chore(main): release 0.22.0 (#748)

* segmentation multitrack (no-mistakes)

* segmentation multitrack (no-mistakes)

* self review

* self review

* recording poll daily doc

* filter cam_audio tracks to remove screensharing from daily processing

* pr review

---------

Co-authored-by: Igor Loskutov <igor.loskutoff@gmail.com>

CHANGELOG.md

@@ -1,5 +1,19 @@
 # Changelog
 
+## [0.22.0](https://github.com/Monadical-SAS/reflector/compare/v0.21.0...v0.22.0) (2025-11-26)
+
+
+### Features
+
+* Multitrack segmentation ([#747](https://github.com/Monadical-SAS/reflector/issues/747)) ([d63040e](https://github.com/Monadical-SAS/reflector/commit/d63040e2fdc07e7b272e85a39eb2411cd6a14798))
+
+## [0.21.0](https://github.com/Monadical-SAS/reflector/compare/v0.20.0...v0.21.0) (2025-11-26)
+
+
+### Features
+
+* add transcript format parameter to GET endpoint ([#709](https://github.com/Monadical-SAS/reflector/issues/709)) ([f6ca075](https://github.com/Monadical-SAS/reflector/commit/f6ca07505f34483b02270a2ef3bd809e9d2e1045))
+
 ## [0.20.0](https://github.com/Monadical-SAS/reflector/compare/v0.19.0...v0.20.0) (2025-11-25)
 
 

docs/transcript.md

@@ -0,0 +1,241 @@
+# Transcript Formats
+
+The Reflector API provides multiple output formats for transcript data through the `transcript_format` query parameter on the GET `/v1/transcripts/{id}` endpoint.
+
+## Overview
+
+When retrieving a transcript, you can specify the desired format using the `transcript_format` query parameter. The API supports four formats optimized for different use cases:
+
+- **text** - Plain text with speaker names (default)
+- **text-timestamped** - Timestamped text with speaker names
+- **webvtt-named** - WebVTT subtitle format with participant names
+- **json** - Structured JSON segments with full metadata
+
+All formats include participant information when available, resolving speaker IDs to actual names.
+
+## Query Parameter Usage
+
+```
+GET /v1/transcripts/{id}?transcript_format={format}
+```
+
+### Parameters
+
+- `transcript_format` (optional): The desired output format
+  - Type: `"text" | "text-timestamped" | "webvtt-named" | "json"`
+  - Default: `"text"`
+
+## Format Descriptions
+
+### Text Format (`text`)
+
+**Use case:** Simple, human-readable transcript for display or export.
+
+**Format:** Speaker names followed by their dialogue, one line per segment.
+
+**Example:**
+```
+John Smith: Hello everyone
+Jane Doe: Hi there
+John Smith: How are you today?
+```
+
+**Request:**
+```bash
+GET /v1/transcripts/{id}?transcript_format=text
+```
+
+**Response:**
+```json
+{
+  "id": "transcript_123",
+  "name": "Meeting Recording",
+  "transcript_format": "text",
+  "transcript": "John Smith: Hello everyone\nJane Doe: Hi there\nJohn Smith: How are you today?",
+  "participants": [
+    {"id": "p1", "speaker": 0, "name": "John Smith"},
+    {"id": "p2", "speaker": 1, "name": "Jane Doe"}
+  ],
+  ...
+}
+```
+
+### Text Timestamped Format (`text-timestamped`)
+
+**Use case:** Transcript with timing information for navigation or reference.
+
+**Format:** `[MM:SS]` timestamp prefix before each speaker and dialogue.
+
+**Example:**
+```
+[00:00] John Smith: Hello everyone
+[00:05] Jane Doe: Hi there
+[00:12] John Smith: How are you today?
+```
+
+**Request:**
+```bash
+GET /v1/transcripts/{id}?transcript_format=text-timestamped
+```
+
+**Response:**
+```json
+{
+  "id": "transcript_123",
+  "name": "Meeting Recording",
+  "transcript_format": "text-timestamped",
+  "transcript": "[00:00] John Smith: Hello everyone\n[00:05] Jane Doe: Hi there\n[00:12] John Smith: How are you today?",
+  "participants": [
+    {"id": "p1", "speaker": 0, "name": "John Smith"},
+    {"id": "p2", "speaker": 1, "name": "Jane Doe"}
+  ],
+  ...
+}
+```
+
+### WebVTT Named Format (`webvtt-named`)
+
+**Use case:** Subtitle files for video players, accessibility tools, or video editing.
+
+**Format:** Standard WebVTT subtitle format with voice tags using participant names.
+
+**Example:**
+```
+WEBVTT
+
+00:00:00.000 --> 00:00:05.000
+<v John Smith>Hello everyone
+
+00:00:05.000 --> 00:00:12.000
+<v Jane Doe>Hi there
+
+00:00:12.000 --> 00:00:18.000
+<v John Smith>How are you today?
+```
+
+**Request:**
+```bash
+GET /v1/transcripts/{id}?transcript_format=webvtt-named
+```
+
+**Response:**
+```json
+{
+  "id": "transcript_123",
+  "name": "Meeting Recording",
+  "transcript_format": "webvtt-named",
+  "transcript": "WEBVTT\n\n00:00:00.000 --> 00:00:05.000\n<v John Smith>Hello everyone\n\n...",
+  "participants": [
+    {"id": "p1", "speaker": 0, "name": "John Smith"},
+    {"id": "p2", "speaker": 1, "name": "Jane Doe"}
+  ],
+  ...
+}
+```
+
+### JSON Format (`json`)
+
+**Use case:** Programmatic access with full timing and speaker metadata.
+
+**Format:** Array of segment objects with speaker information, text content, and precise timing.
+
+**Example:**
+```json
+[
+  {
+    "speaker": 0,
+    "speaker_name": "John Smith",
+    "text": "Hello everyone",
+    "start": 0.0,
+    "end": 5.0
+  },
+  {
+    "speaker": 1,
+    "speaker_name": "Jane Doe",
+    "text": "Hi there",
+    "start": 5.0,
+    "end": 12.0
+  },
+  {
+    "speaker": 0,
+    "speaker_name": "John Smith",
+    "text": "How are you today?",
+    "start": 12.0,
+    "end": 18.0
+  }
+]
+```
+
+**Request:**
+```bash
+GET /v1/transcripts/{id}?transcript_format=json
+```
+
+**Response:**
+```json
+{
+  "id": "transcript_123",
+  "name": "Meeting Recording",
+  "transcript_format": "json",
+  "transcript": [
+    {
+      "speaker": 0,
+      "speaker_name": "John Smith",
+      "text": "Hello everyone",
+      "start": 0.0,
+      "end": 5.0
+    },
+    {
+      "speaker": 1,
+      "speaker_name": "Jane Doe",
+      "text": "Hi there",
+      "start": 5.0,
+      "end": 12.0
+    }
+  ],
+  "participants": [
+    {"id": "p1", "speaker": 0, "name": "John Smith"},
+    {"id": "p2", "speaker": 1, "name": "Jane Doe"}
+  ],
+  ...
+}
+```
+
+## Response Structure
+
+All formats return the same base transcript metadata with an additional `transcript_format` field and format-specific `transcript` field:
+
+### Common Fields
+
+- `id`: Transcript identifier
+- `user_id`: Owner user ID (if authenticated)
+- `name`: Transcript name
+- `status`: Processing status
+- `locked`: Whether transcript is locked for editing
+- `duration`: Total duration in seconds
+- `title`: Auto-generated or custom title
+- `short_summary`: Brief summary
+- `long_summary`: Detailed summary
+- `created_at`: Creation timestamp
+- `share_mode`: Access control setting
+- `source_language`: Original audio language
+- `target_language`: Translation target language
+- `reviewed`: Whether transcript has been reviewed
+- `meeting_id`: Associated meeting ID (if applicable)
+- `source_kind`: Source type (live, file, room)
+- `room_id`: Associated room ID (if applicable)
+- `audio_deleted`: Whether audio has been deleted
+- `participants`: Array of participant objects with speaker mappings
+
+### Format-Specific Fields
+
+- `transcript_format`: The format identifier (discriminator field)
+- `transcript`: The formatted transcript content (string for text/webvtt formats, array for json format)
+
+## Speaker Name Resolution
+
+All formats resolve speaker IDs to participant names when available:
+
+- If a participant exists for the speaker ID, their name is used
+- If no participant exists, a default name like "Speaker 0" is generated
+- Speaker IDs are integers (0, 1, 2, etc.) assigned during diarization

server/reflector/db/recordings.py

@@ -35,8 +35,15 @@ class Recording(BaseModel):
     status: Literal["pending", "processing", "completed", "failed"] = "pending"
     meeting_id: str | None = None
     # for multitrack reprocessing
+    # track_keys can be empty list [] if recording finished but no audio was captured (silence/muted)
+    # None means not a multitrack recording, [] means multitrack with no tracks
     track_keys: list[str] | None = None
 
+    @property
+    def is_multitrack(self) -> bool:
+        """True if recording has separate audio tracks (1+ tracks counts as multitrack)."""
+        return self.track_keys is not None and len(self.track_keys) > 0
+
 
 class RecordingController:
     async def create(self, recording: Recording):

server/reflector/processors/types.py

@@ -1,6 +1,7 @@
 import io
 import re
 import tempfile
+from collections import defaultdict
 from pathlib import Path
 from typing import Annotated, TypedDict
 
@@ -16,6 +17,17 @@ class DiarizationSegment(TypedDict):
 
 
 PUNC_RE = re.compile(r"[.;:?!…]")
+SENTENCE_END_RE = re.compile(r"[.?!…]$")
+
+# Max segment length for words_to_segments() - breaks on any punctuation (. ; : ? ! …)
+# when segment exceeds this limit. Used for non-multitrack recordings.
+MAX_SEGMENT_CHARS = 120
+
+# Max segment length for words_to_segments_by_sentence() - only breaks on sentence-ending
+# punctuation (. ? ! …) when segment exceeds this limit. Higher threshold allows complete
+# sentences in multitrack recordings where speakers overlap.
+# similar number to server/reflector/processors/transcript_liner.py
+MAX_SENTENCE_SEGMENT_CHARS = 1000
 
 
 class AudioFile(BaseModel):
@@ -76,7 +88,6 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
     # but separate if the speaker changes, or if the punctuation is a . , ; : ? !
     segments = []
     current_segment = None
-    MAX_SEGMENT_LENGTH = 120
 
     for word in words:
         if current_segment is None:
@@ -106,7 +117,7 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
         current_segment.end = word.end
 
         have_punc = PUNC_RE.search(word.text)
-        if have_punc and (len(current_segment.text) > MAX_SEGMENT_LENGTH):
+        if have_punc and (len(current_segment.text) > MAX_SEGMENT_CHARS):
             segments.append(current_segment)
             current_segment = None
 
@@ -116,6 +127,70 @@ def words_to_segments(words: list[Word]) -> list[TranscriptSegment]:
     return segments
 
 
+def words_to_segments_by_sentence(words: list[Word]) -> list[TranscriptSegment]:
+    """Group words by speaker, then split into sentences.
+
+    For multitrack recordings where words from different speakers are interleaved
+    by timestamp, this function first groups all words by speaker, then creates
+    segments based on sentence boundaries within each speaker's words.
+
+    This produces cleaner output than words_to_segments() which breaks on every
+    speaker change, resulting in many tiny segments when speakers overlap.
+    """
+    if not words:
+        return []
+
+    # Group words by speaker, preserving order within each speaker
+    by_speaker: dict[int, list[Word]] = defaultdict(list)
+    for w in words:
+        by_speaker[w.speaker].append(w)
+
+    segments: list[TranscriptSegment] = []
+
+    for speaker, speaker_words in by_speaker.items():
+        current_text = ""
+        current_start: float | None = None
+        current_end: float = 0.0
+
+        for word in speaker_words:
+            if current_start is None:
+                current_start = word.start
+
+            current_text += word.text
+            current_end = word.end
+
+            # Check for sentence end or max length
+            is_sentence_end = SENTENCE_END_RE.search(word.text.strip())
+            is_too_long = len(current_text) >= MAX_SENTENCE_SEGMENT_CHARS
+
+            if is_sentence_end or is_too_long:
+                segments.append(
+                    TranscriptSegment(
+                        text=current_text,
+                        start=current_start,
+                        end=current_end,
+                        speaker=speaker,
+                    )
+                )
+                current_text = ""
+                current_start = None
+
+        # Flush remaining words for this speaker
+        if current_text and current_start is not None:
+            segments.append(
+                TranscriptSegment(
+                    text=current_text,
+                    start=current_start,
+                    end=current_end,
+                    speaker=speaker,
+                )
+            )
+
+    # Sort segments by start time
+    segments.sort(key=lambda s: s.start)
+    return segments
+
+
 class Transcript(BaseModel):
     translation: str | None = None
     words: list[Word] = []
@@ -154,7 +229,9 @@ class Transcript(BaseModel):
             word.start += offset
             word.end += offset
 
-    def as_segments(self) -> list[TranscriptSegment]:
+    def as_segments(self, is_multitrack: bool = False) -> list[TranscriptSegment]:
+        if is_multitrack:
+            return words_to_segments_by_sentence(self.words)
         return words_to_segments(self.words)
 
 

server/reflector/schemas/transcript_formats.py

@@ -0,0 +1,17 @@
+"""Schema definitions for transcript format types and segments."""
+
+from typing import Literal
+
+from pydantic import BaseModel
+
+TranscriptFormat = Literal["text", "text-timestamped", "webvtt-named", "json"]
+
+
+class TranscriptSegment(BaseModel):
+    """A single transcript segment with speaker and timing information."""
+
+    speaker: int
+    speaker_name: str
+    text: str
+    start: float
+    end: float

server/reflector/services/transcript_process.py

@@ -7,7 +7,7 @@ This module provides result-based error handling that works in both contexts:
 """
 
 from dataclasses import dataclass
-from typing import Literal, Union
+from typing import Literal, Union, assert_never
 
 import celery
 from celery.result import AsyncResult
@@ -18,7 +18,6 @@ from reflector.pipelines.main_file_pipeline import task_pipeline_file_process
 from reflector.pipelines.main_multitrack_pipeline import (
     task_pipeline_multitrack_process,
 )
-from reflector.utils.match import absurd
 from reflector.utils.string import NonEmptyString
 
 
@@ -155,7 +154,7 @@ def dispatch_transcript_processing(config: ProcessingConfig) -> AsyncResult:
     elif isinstance(config, FileProcessingConfig):
         return task_pipeline_file_process.delay(transcript_id=config.transcript_id)
     else:
-        absurd(config)
+        assert_never(config)
 
 
 def task_is_scheduled_or_active(task_name: str, **kwargs):

server/reflector/utils/daily.py

@@ -64,6 +64,11 @@ def recording_lock_key(recording_id: NonEmptyString) -> NonEmptyString:
     return f"recording:{recording_id}"
 
 
+def filter_cam_audio_tracks(track_keys: list[str]) -> list[str]:
+    """Filter track keys to cam-audio tracks only (skip screen-audio, etc.)."""
+    return [k for k in track_keys if "cam-audio" in k]
+
+
 def extract_base_room_name(daily_room_name: DailyRoomName) -> NonEmptyString:
     """
     Extract base room name from Daily.co timestamped room name.

server/reflector/utils/match.py

@@ -1,10 +0,0 @@
-from typing import NoReturn
-
-
-def assert_exhaustiveness(x: NoReturn) -> NoReturn:
-    """Provide an assertion at type-check time that this function is never called."""
-    raise AssertionError(f"Invalid value: {x!r}")
-
-
-def absurd(x: NoReturn) -> NoReturn:
-    return assert_exhaustiveness(x)

server/reflector/utils/transcript_formats.py

@@ -0,0 +1,133 @@
+"""Utilities for converting transcript data to various output formats."""
+
+import webvtt
+
+from reflector.db.transcripts import TranscriptParticipant, TranscriptTopic
+from reflector.processors.types import (
+    Transcript as ProcessorTranscript,
+)
+from reflector.schemas.transcript_formats import TranscriptSegment
+from reflector.utils.webvtt import seconds_to_timestamp
+
+
+def get_speaker_name(
+    speaker: int, participants: list[TranscriptParticipant] | None
+) -> str:
+    """Get participant name for speaker or default to 'Speaker N'."""
+    if participants:
+        for participant in participants:
+            if participant.speaker == speaker:
+                return participant.name
+    return f"Speaker {speaker}"
+
+
+def format_timestamp_mmss(seconds: float | int) -> str:
+    """Format seconds as MM:SS timestamp."""
+    minutes = int(seconds // 60)
+    secs = int(seconds % 60)
+    return f"{minutes:02d}:{secs:02d}"
+
+
+def transcript_to_text(
+    topics: list[TranscriptTopic],
+    participants: list[TranscriptParticipant] | None,
+    is_multitrack: bool = False,
+) -> str:
+    """Convert transcript topics to plain text with speaker names."""
+    lines = []
+    for topic in topics:
+        if not topic.words:
+            continue
+
+        transcript = ProcessorTranscript(words=topic.words)
+        segments = transcript.as_segments(is_multitrack)
+
+        for segment in segments:
+            speaker_name = get_speaker_name(segment.speaker, participants)
+            text = segment.text.strip()
+            lines.append(f"{speaker_name}: {text}")
+
+    return "\n".join(lines)
+
+
+def transcript_to_text_timestamped(
+    topics: list[TranscriptTopic],
+    participants: list[TranscriptParticipant] | None,
+    is_multitrack: bool = False,
+) -> str:
+    """Convert transcript topics to timestamped text with speaker names."""
+    lines = []
+    for topic in topics:
+        if not topic.words:
+            continue
+
+        transcript = ProcessorTranscript(words=topic.words)
+        segments = transcript.as_segments(is_multitrack)
+
+        for segment in segments:
+            speaker_name = get_speaker_name(segment.speaker, participants)
+            timestamp = format_timestamp_mmss(segment.start)
+            text = segment.text.strip()
+            lines.append(f"[{timestamp}] {speaker_name}: {text}")
+
+    return "\n".join(lines)
+
+
+def topics_to_webvtt_named(
+    topics: list[TranscriptTopic],
+    participants: list[TranscriptParticipant] | None,
+    is_multitrack: bool = False,
+) -> str:
+    """Convert transcript topics to WebVTT format with participant names."""
+    vtt = webvtt.WebVTT()
+
+    for topic in topics:
+        if not topic.words:
+            continue
+
+        transcript = ProcessorTranscript(words=topic.words)
+        segments = transcript.as_segments(is_multitrack)
+
+        for segment in segments:
+            speaker_name = get_speaker_name(segment.speaker, participants)
+            text = segment.text.strip()
+            text = f"<v {speaker_name}>{text}"
+
+            caption = webvtt.Caption(
+                start=seconds_to_timestamp(segment.start),
+                end=seconds_to_timestamp(segment.end),
+                text=text,
+            )
+            vtt.captions.append(caption)
+
+    return vtt.content
+
+
+def transcript_to_json_segments(
+    topics: list[TranscriptTopic],
+    participants: list[TranscriptParticipant] | None,
+    is_multitrack: bool = False,
+) -> list[TranscriptSegment]:
+    """Convert transcript topics to a flat list of JSON segments."""
+    result = []
+
+    for topic in topics:
+        if not topic.words:
+            continue
+
+        transcript = ProcessorTranscript(words=topic.words)
+        segments = transcript.as_segments(is_multitrack)
+
+        for segment in segments:
+            speaker_name = get_speaker_name(segment.speaker, participants)
+            result.append(
+                TranscriptSegment(
+                    speaker=segment.speaker,
+                    speaker_name=speaker_name,
+                    text=segment.text.strip(),
+                    start=segment.start,
+                    end=segment.end,
+                )
+            )
+
+    return result

server/reflector/utils/webvtt.py

@@ -13,7 +13,7 @@ VttTimestamp = Annotated[str, "vtt_timestamp"]
 WebVTTStr = Annotated[str, "webvtt_str"]
 
 
-def _seconds_to_timestamp(seconds: Seconds) -> VttTimestamp:
+def seconds_to_timestamp(seconds: Seconds) -> VttTimestamp:
     # lib doesn't do that
     hours = int(seconds // 3600)
     minutes = int((seconds % 3600) // 60)
@@ -37,8 +37,8 @@ def words_to_webvtt(words: list[Word]) -> WebVTTStr:
         text = f"<v Speaker{segment.speaker}>{text}"
 
         caption = webvtt.Caption(
-            start=_seconds_to_timestamp(segment.start),
-            end=_seconds_to_timestamp(segment.end),
+            start=seconds_to_timestamp(segment.start),
+            end=seconds_to_timestamp(segment.end),
             text=text,
         )
         vtt.captions.append(caption)

server/reflector/video_platforms/daily.py

@@ -173,15 +173,16 @@ class DailyClient(VideoPlatformClient):
         self,
         room_name: DailyRoomName,
         enable_recording: bool,
-        user_id: str | None = None,
-    ) -> str:
+        user_id: NonEmptyString | None = None,
+        is_owner: bool = False,
+    ) -> NonEmptyString:
         properties = MeetingTokenProperties(
             room_name=room_name,
             user_id=user_id,
             start_cloud_recording=enable_recording,
-            enable_recording_ui=not enable_recording,
+            enable_recording_ui=False,
+            is_owner=is_owner,
         )
-
         request = CreateMeetingTokenRequest(properties=properties)
         result = await self._api_client.create_meeting_token(request)
         return result.token

server/reflector/views/rooms.py

@@ -248,7 +248,7 @@ async def rooms_create(
         ics_url=room.ics_url,
         ics_fetch_interval=room.ics_fetch_interval,
         ics_enabled=room.ics_enabled,
-        platform=room.platform,
+        platform=room.platform or settings.DEFAULT_VIDEO_PLATFORM,
     )
 
 
@@ -556,6 +556,7 @@ async def rooms_join_meeting(
             meeting.room_name,
             enable_recording=enable_recording,
             user_id=user_id,
+            is_owner=user_id == room.user_id,
         )
         meeting = meeting.model_copy()
         meeting.room_url = add_query_param(meeting.room_url, "t", token)

server/reflector/views/transcripts.py

@@ -1,14 +1,22 @@
 from datetime import datetime, timedelta, timezone
-from typing import Annotated, Literal, Optional
+from typing import Annotated, Literal, Optional, assert_never
 
 from fastapi import APIRouter, Depends, HTTPException, Query
 from fastapi_pagination import Page
 from fastapi_pagination.ext.databases import apaginate
 from jose import jwt
-from pydantic import AwareDatetime, BaseModel, Field, constr, field_serializer
+from pydantic import (
+    AwareDatetime,
+    BaseModel,
+    Discriminator,
+    Field,
+    constr,
+    field_serializer,
+)
 
 import reflector.auth as auth
 from reflector.db import get_database
+from reflector.db.recordings import recordings_controller
 from reflector.db.search import (
     DEFAULT_SEARCH_LIMIT,
     SearchLimit,
@@ -31,7 +39,14 @@ from reflector.db.transcripts import (
 )
 from reflector.processors.types import Transcript as ProcessorTranscript
 from reflector.processors.types import Word
+from reflector.schemas.transcript_formats import TranscriptFormat, TranscriptSegment
 from reflector.settings import settings
+from reflector.utils.transcript_formats import (
+    topics_to_webvtt_named,
+    transcript_to_json_segments,
+    transcript_to_text,
+    transcript_to_text_timestamped,
+)
 from reflector.ws_manager import get_ws_manager
 from reflector.zulip import (
     InvalidMessageError,
@@ -46,6 +61,14 @@ ALGORITHM = "HS256"
 DOWNLOAD_EXPIRE_MINUTES = 60
 
 
+async def _get_is_multitrack(transcript) -> bool:
+    """Detect if transcript is from multitrack recording."""
+    if not transcript.recording_id:
+        return False
+    recording = await recordings_controller.get_by_id(transcript.recording_id)
+    return recording is not None and recording.is_multitrack
+
+
 def create_access_token(data: dict, expires_delta: timedelta):
     to_encode = data.copy()
     expire = datetime.now(timezone.utc) + expires_delta
@@ -88,10 +111,84 @@ class GetTranscriptMinimal(BaseModel):
     audio_deleted: bool | None = None
 
 
-class GetTranscript(GetTranscriptMinimal):
+class GetTranscriptWithParticipants(GetTranscriptMinimal):
     participants: list[TranscriptParticipant] | None
 
 
+class GetTranscriptWithText(GetTranscriptWithParticipants):
+    """
+    Transcript response with plain text format.
+
+    Format: Speaker names followed by their dialogue, one line per segment.
+    Example:
+        John Smith: Hello everyone
+        Jane Doe: Hi there
+    """
+
+    transcript_format: Literal["text"] = "text"
+    transcript: str
+
+
+class GetTranscriptWithTextTimestamped(GetTranscriptWithParticipants):
+    """
+    Transcript response with timestamped text format.
+
+    Format: [MM:SS] timestamp prefix before each speaker and dialogue.
+    Example:
+        [00:00] John Smith: Hello everyone
+        [00:05] Jane Doe: Hi there
+    """
+
+    transcript_format: Literal["text-timestamped"] = "text-timestamped"
+    transcript: str
+
+
+class GetTranscriptWithWebVTTNamed(GetTranscriptWithParticipants):
+    """
+    Transcript response in WebVTT subtitle format with participant names.
+
+    Format: Standard WebVTT with voice tags using participant names.
+    Example:
+        WEBVTT
+
+        00:00:00.000 --> 00:00:05.000
+        <v John Smith>Hello everyone
+    """
+
+    transcript_format: Literal["webvtt-named"] = "webvtt-named"
+    transcript: str
+
+
+class GetTranscriptWithJSON(GetTranscriptWithParticipants):
+    """
+    Transcript response as structured JSON segments.
+
+    Format: Array of segment objects with speaker info, text, and timing.
+    Example:
+        [
+            {
+                "speaker": 0,
+                "speaker_name": "John Smith",
+                "text": "Hello everyone",
+                "start": 0.0,
+                "end": 5.0
+            }
+        ]
+    """
+
+    transcript_format: Literal["json"] = "json"
+    transcript: list[TranscriptSegment]
+
+
+GetTranscript = Annotated[
+    GetTranscriptWithText
+    | GetTranscriptWithTextTimestamped
+    | GetTranscriptWithWebVTTNamed
+    | GetTranscriptWithJSON,
+    Discriminator("transcript_format"),
+]
+
+
 class CreateTranscript(BaseModel):
     name: str
     source_language: str = Field("en")
@@ -228,7 +325,7 @@ async def transcripts_search(
     )
 
 
-@router.post("/transcripts", response_model=GetTranscript)
+@router.post("/transcripts", response_model=GetTranscriptWithParticipants)
 async def transcripts_create(
     info: CreateTranscript,
     user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
@@ -272,7 +369,7 @@ class GetTranscriptTopic(BaseModel):
     segments: list[GetTranscriptSegmentTopic] = []
 
     @classmethod
-    def from_transcript_topic(cls, topic: TranscriptTopic):
+    def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
         if not topic.words:
             # In previous version, words were missing
             # Just output a segment with speaker 0
@@ -296,7 +393,7 @@ class GetTranscriptTopic(BaseModel):
                     start=segment.start,
                     speaker=segment.speaker,
                 )
-                for segment in transcript.as_segments()
+                for segment in transcript.as_segments(is_multitrack)
             ]
         return cls(
             id=topic.id,
@@ -313,8 +410,8 @@ class GetTranscriptTopicWithWords(GetTranscriptTopic):
     words: list[Word] = []
 
     @classmethod
-    def from_transcript_topic(cls, topic: TranscriptTopic):
-        instance = super().from_transcript_topic(topic)
+    def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
+        instance = super().from_transcript_topic(topic, is_multitrack)
         if topic.words:
             instance.words = topic.words
         return instance
@@ -329,8 +426,8 @@ class GetTranscriptTopicWithWordsPerSpeaker(GetTranscriptTopic):
     words_per_speaker: list[SpeakerWords] = []
 
     @classmethod
-    def from_transcript_topic(cls, topic: TranscriptTopic):
-        instance = super().from_transcript_topic(topic)
+    def from_transcript_topic(cls, topic: TranscriptTopic, is_multitrack: bool = False):
+        instance = super().from_transcript_topic(topic, is_multitrack)
         if topic.words:
             words_per_speakers = []
             # group words by speaker
@@ -362,14 +459,76 @@ class GetTranscriptTopicWithWordsPerSpeaker(GetTranscriptTopic):
 async def transcript_get(
     transcript_id: str,
     user: Annotated[Optional[auth.UserInfo], Depends(auth.current_user_optional)],
+    transcript_format: TranscriptFormat = "text",
 ):
     user_id = user["sub"] if user else None
-    return await transcripts_controller.get_by_id_for_http(
+    transcript = await transcripts_controller.get_by_id_for_http(
         transcript_id, user_id=user_id
     )
 
+    is_multitrack = await _get_is_multitrack(transcript)
 
-@router.patch("/transcripts/{transcript_id}", response_model=GetTranscript)
+    base_data = {
+        "id": transcript.id,
+        "user_id": transcript.user_id,
+        "name": transcript.name,
+        "status": transcript.status,
+        "locked": transcript.locked,
+        "duration": transcript.duration,
+        "title": transcript.title,
+        "short_summary": transcript.short_summary,
+        "long_summary": transcript.long_summary,
+        "created_at": transcript.created_at,
+        "share_mode": transcript.share_mode,
+        "source_language": transcript.source_language,
+        "target_language": transcript.target_language,
+        "reviewed": transcript.reviewed,
+        "meeting_id": transcript.meeting_id,
+        "source_kind": transcript.source_kind,
+        "room_id": transcript.room_id,
+        "audio_deleted": transcript.audio_deleted,
+        "participants": transcript.participants,
+    }
+
+    if transcript_format == "text":
+        return GetTranscriptWithText(
+            **base_data,
+            transcript_format="text",
+            transcript=transcript_to_text(
+                transcript.topics, transcript.participants, is_multitrack
+            ),
+        )
+    elif transcript_format == "text-timestamped":
+        return GetTranscriptWithTextTimestamped(
+            **base_data,
+            transcript_format="text-timestamped",
+            transcript=transcript_to_text_timestamped(
+                transcript.topics, transcript.participants, is_multitrack
+            ),
+        )
+    elif transcript_format == "webvtt-named":
+        return GetTranscriptWithWebVTTNamed(
+            **base_data,
+            transcript_format="webvtt-named",
+            transcript=topics_to_webvtt_named(
+                transcript.topics, transcript.participants, is_multitrack
+            ),
+        )
+    elif transcript_format == "json":
+        return GetTranscriptWithJSON(
+            **base_data,
+            transcript_format="json",
+            transcript=transcript_to_json_segments(
+                transcript.topics, transcript.participants, is_multitrack
+            ),
+        )
+    else:
+        assert_never(transcript_format)
+
+
+@router.patch(
+    "/transcripts/{transcript_id}", response_model=GetTranscriptWithParticipants
+)
 async def transcript_update(
     transcript_id: str,
     info: UpdateTranscript,
@@ -419,9 +578,12 @@ async def transcript_get_topics(
         transcript_id, user_id=user_id
     )
 
+    is_multitrack = await _get_is_multitrack(transcript)
+
     # convert to GetTranscriptTopic
     return [
-        GetTranscriptTopic.from_transcript_topic(topic) for topic in transcript.topics
+        GetTranscriptTopic.from_transcript_topic(topic, is_multitrack)
+        for topic in transcript.topics
     ]
 
 
@@ -438,9 +600,11 @@ async def transcript_get_topics_with_words(
         transcript_id, user_id=user_id
     )
 
+    is_multitrack = await _get_is_multitrack(transcript)
+
     # convert to GetTranscriptTopicWithWords
     return [
-        GetTranscriptTopicWithWords.from_transcript_topic(topic)
+        GetTranscriptTopicWithWords.from_transcript_topic(topic, is_multitrack)
         for topic in transcript.topics
     ]
 
@@ -459,13 +623,17 @@ async def transcript_get_topics_with_words_per_speaker(
         transcript_id, user_id=user_id
     )
 
+    is_multitrack = await _get_is_multitrack(transcript)
+
     # get the topic from the transcript
     topic = next((t for t in transcript.topics if t.id == topic_id), None)
     if not topic:
         raise HTTPException(status_code=404, detail="Topic not found")
 
     # convert to GetTranscriptTopicWithWordsPerSpeaker
-    return GetTranscriptTopicWithWordsPerSpeaker.from_transcript_topic(topic)
+    return GetTranscriptTopicWithWordsPerSpeaker.from_transcript_topic(
+        topic, is_multitrack
+    )
 
 
 @router.post("/transcripts/{transcript_id}/zulip")

server/reflector/views/transcripts_process.py

@@ -1,4 +1,4 @@
-from typing import Annotated, Optional
+from typing import Annotated, Optional, assert_never
 
 from fastapi import APIRouter, Depends, HTTPException
 from pydantic import BaseModel
@@ -15,7 +15,6 @@ from reflector.services.transcript_process import (
     prepare_transcript_processing,
     validate_transcript_for_processing,
 )
-from reflector.utils.match import absurd
 
 router = APIRouter()
 
@@ -44,7 +43,7 @@ async def transcript_process(
     elif isinstance(validation, ValidationOk):
         pass
     else:
-        absurd(validation)
+        assert_never(validation)
 
     config = await prepare_transcript_processing(validation)
 

server/reflector/worker/process.py

@@ -2,6 +2,7 @@ import json
 import os
 import re
 from datetime import datetime, timezone
+from typing import List
 from urllib.parse import unquote
 
 import av
@@ -11,7 +12,7 @@ from celery import shared_task
 from celery.utils.log import get_task_logger
 from pydantic import ValidationError
 
-from reflector.dailyco_api import MeetingParticipantsResponse
+from reflector.dailyco_api import MeetingParticipantsResponse, RecordingResponse
 from reflector.db.daily_participant_sessions import (
     DailyParticipantSession,
     daily_participant_sessions_controller,
@@ -38,6 +39,7 @@ from reflector.storage import get_transcripts_storage
 from reflector.utils.daily import (
     DailyRoomName,
     extract_base_room_name,
+    filter_cam_audio_tracks,
     parse_daily_recording_filename,
     recording_lock_key,
 )
@@ -338,7 +340,9 @@ async def _process_multitrack_recording_inner(
                     exc_info=True,
                 )
 
-            for idx, key in enumerate(track_keys):
+            cam_audio_keys = filter_cam_audio_tracks(track_keys)
+
+            for idx, key in enumerate(cam_audio_keys):
                 try:
                     parsed = parse_daily_recording_filename(key)
                     participant_id = parsed.participant_id
@@ -366,7 +370,7 @@ async def _process_multitrack_recording_inner(
     task_pipeline_multitrack_process.delay(
         transcript_id=transcript.id,
         bucket_name=bucket_name,
-        track_keys=track_keys,
+        track_keys=filter_cam_audio_tracks(track_keys),
     )
 
 
@@ -391,7 +395,7 @@ async def poll_daily_recordings():
 
     async with create_platform_client("daily") as daily_client:
         # latest 100. TODO cursor-based state
-        api_recordings = await daily_client.list_recordings()
+        api_recordings: List[RecordingResponse] = await daily_client.list_recordings()
 
     if not api_recordings:
         logger.debug(
@@ -422,11 +426,13 @@ async def poll_daily_recordings():
 
     for recording in missing_recordings:
         if not recording.tracks:
-            assert recording.status != "finished", (
-                f"Recording {recording.id} has status='finished' but no tracks. "
-                f"Daily.co API guarantees finished recordings have tracks available. "
-                f"room_name={recording.room_name}"
+            if recording.status == "finished":
+                logger.warning(
+                    "Finished recording has no tracks (no audio captured)",
+                    recording_id=recording.id,
+                    room_name=recording.room_name,
                 )
+            else:
                 logger.debug(
                     "No tracks in recording yet",
                     recording_id=recording.id,

server/tests/test_processor_transcript_segment.py

@@ -159,3 +159,78 @@ def test_processor_transcript_segment():
     assert segments[3].start == 30.72
     assert segments[4].start == 31.56
     assert segments[5].start == 32.38
+
+
+def test_processor_transcript_segment_multitrack_interleaved():
+    """Test as_segments(is_multitrack=True) with interleaved speakers.
+
+    Multitrack recordings have words from different speakers sorted by start time,
+    causing frequent speaker alternation. The multitrack mode should group by
+    speaker first, then split into sentences.
+    """
+    from reflector.processors.types import Transcript, Word
+
+    # Simulate real multitrack data: words sorted by start time, speakers interleave
+    # Speaker 0 says: "Hello there."
+    # Speaker 1 says: "I'm good."
+    # When sorted by time, words interleave
+    transcript = Transcript(
+        words=[
+            Word(text="Hello ", start=0.0, end=0.5, speaker=0),
+            Word(text="I'm ", start=0.5, end=0.8, speaker=1),
+            Word(text="there.", start=0.5, end=1.0, speaker=0),
+            Word(text="good.", start=1.0, end=1.5, speaker=1),
+        ]
+    )
+
+    # Default behavior (is_multitrack=False): breaks on every speaker change = 4 segments
+    segments_default = transcript.as_segments(is_multitrack=False)
+    assert len(segments_default) == 4
+
+    # Multitrack behavior: groups by speaker, then sentences = 2 segments
+    segments_multitrack = transcript.as_segments(is_multitrack=True)
+    assert len(segments_multitrack) == 2
+
+    # Check content - sorted by start time
+    assert segments_multitrack[0].speaker == 0
+    assert segments_multitrack[0].text == "Hello there."
+    assert segments_multitrack[0].start == 0.0
+    assert segments_multitrack[0].end == 1.0
+
+    assert segments_multitrack[1].speaker == 1
+    assert segments_multitrack[1].text == "I'm good."
+    assert segments_multitrack[1].start == 0.5
+    assert segments_multitrack[1].end == 1.5
+
+
+def test_processor_transcript_segment_multitrack_overlapping_timestamps():
+    """Test multitrack with exactly overlapping timestamps (real Daily.co data pattern)."""
+    from reflector.processors.types import Transcript, Word
+
+    # Real pattern from transcript 38d84d57: words with identical timestamps
+    transcript = Transcript(
+        words=[
+            Word(text="speaking ", start=6.71, end=7.11, speaker=0),
+            Word(text="Speaking ", start=6.71, end=7.11, speaker=1),
+            Word(text="at ", start=7.11, end=7.27, speaker=0),
+            Word(text="at ", start=7.11, end=7.27, speaker=1),
+            Word(text="the ", start=7.27, end=7.43, speaker=0),
+            Word(text="the ", start=7.27, end=7.43, speaker=1),
+            Word(text="same ", start=7.43, end=7.59, speaker=0),
+            Word(text="same ", start=7.43, end=7.59, speaker=1),
+            Word(text="time.", start=7.59, end=8.0, speaker=0),
+            Word(text="time.", start=7.59, end=8.0, speaker=1),
+        ]
+    )
+
+    # Default: 10 segments (one per speaker change)
+    segments_default = transcript.as_segments(is_multitrack=False)
+    assert len(segments_default) == 10
+
+    # Multitrack: 2 segments (one per speaker sentence)
+    segments_multitrack = transcript.as_segments(is_multitrack=True)
+    assert len(segments_multitrack) == 2
+
+    # Both should have complete sentences
+    assert "speaking at the same time." in segments_multitrack[0].text
+    assert "Speaking at the same time." in segments_multitrack[1].text

server/tests/test_transcript_formats.py

@@ -0,0 +1,779 @@
+"""Tests for transcript format conversion functionality."""
+
+import pytest
+
+from reflector.db.transcripts import TranscriptParticipant, TranscriptTopic
+from reflector.processors.types import Word
+from reflector.utils.transcript_formats import (
+    format_timestamp_mmss,
+    get_speaker_name,
+    topics_to_webvtt_named,
+    transcript_to_json_segments,
+    transcript_to_text,
+    transcript_to_text_timestamped,
+)
+
+
+@pytest.mark.asyncio
+async def test_get_speaker_name_with_participants():
+    """Test speaker name resolution with participants list."""
+    participants = [
+        TranscriptParticipant(id="1", speaker=0, name="John Smith"),
+        TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
+    ]
+
+    assert get_speaker_name(0, participants) == "John Smith"
+    assert get_speaker_name(1, participants) == "Jane Doe"
+    assert get_speaker_name(2, participants) == "Speaker 2"
+
+
+@pytest.mark.asyncio
+async def test_get_speaker_name_without_participants():
+    """Test speaker name resolution without participants list."""
+    assert get_speaker_name(0, None) == "Speaker 0"
+    assert get_speaker_name(1, None) == "Speaker 1"
+    assert get_speaker_name(5, []) == "Speaker 5"
+
+
+@pytest.mark.asyncio
+async def test_format_timestamp_mmss():
+    """Test timestamp formatting to MM:SS."""
+    assert format_timestamp_mmss(0) == "00:00"
+    assert format_timestamp_mmss(5) == "00:05"
+    assert format_timestamp_mmss(65) == "01:05"
+    assert format_timestamp_mmss(125.7) == "02:05"
+    assert format_timestamp_mmss(3661) == "61:01"
+
+
+@pytest.mark.asyncio
+async def test_transcript_to_text():
+    """Test plain text format conversion."""
+    topics = [
+        TranscriptTopic(
+            id="1",
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0.0,
+            words=[
+                Word(text="Hello", start=0.0, end=1.0, speaker=0),
+                Word(text=" world.", start=1.0, end=2.0, speaker=0),
+            ],
+        ),
+        TranscriptTopic(
+            id="2",
+            title="Topic 2",
+            summary="Summary 2",
+            timestamp=2.0,
+            words=[
+                Word(text="How", start=2.0, end=3.0, speaker=1),
+                Word(text=" are", start=3.0, end=4.0, speaker=1),
+                Word(text=" you?", start=4.0, end=5.0, speaker=1),
+            ],
+        ),
+    ]
+
+    participants = [
+        TranscriptParticipant(id="1", speaker=0, name="John Smith"),
+        TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
+    ]
+
+    result = transcript_to_text(topics, participants)
+    lines = result.split("\n")
+
+    assert len(lines) == 2
+    assert lines[0] == "John Smith: Hello world."
+    assert lines[1] == "Jane Doe: How are you?"
+
+
+@pytest.mark.asyncio
+async def test_transcript_to_text_timestamped():
+    """Test timestamped text format conversion."""
+    topics = [
+        TranscriptTopic(
+            id="1",
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0.0,
+            words=[
+                Word(text="Hello", start=0.0, end=1.0, speaker=0),
+                Word(text=" world.", start=1.0, end=2.0, speaker=0),
+            ],
+        ),
+        TranscriptTopic(
+            id="2",
+            title="Topic 2",
+            summary="Summary 2",
+            timestamp=65.0,
+            words=[
+                Word(text="How", start=65.0, end=66.0, speaker=1),
+                Word(text=" are", start=66.0, end=67.0, speaker=1),
+                Word(text=" you?", start=67.0, end=68.0, speaker=1),
+            ],
+        ),
+    ]
+
+    participants = [
+        TranscriptParticipant(id="1", speaker=0, name="John Smith"),
+        TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
+    ]
+
+    result = transcript_to_text_timestamped(topics, participants)
+    lines = result.split("\n")
+
+    assert len(lines) == 2
+    assert lines[0] == "[00:00] John Smith: Hello world."
+    assert lines[1] == "[01:05] Jane Doe: How are you?"
+
+
+@pytest.mark.asyncio
+async def test_topics_to_webvtt_named():
+    """Test WebVTT format conversion with participant names."""
+    topics = [
+        TranscriptTopic(
+            id="1",
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0.0,
+            words=[
+                Word(text="Hello", start=0.0, end=1.0, speaker=0),
+                Word(text=" world.", start=1.0, end=2.0, speaker=0),
+            ],
+        ),
+    ]
+
+    participants = [
+        TranscriptParticipant(id="1", speaker=0, name="John Smith"),
+    ]
+
+    result = topics_to_webvtt_named(topics, participants)
+
+    assert result.startswith("WEBVTT")
+    assert "<v John Smith>" in result
+    assert "00:00:00.000 --> 00:00:02.000" in result
+    assert "Hello world." in result
+
+
+@pytest.mark.asyncio
+async def test_transcript_to_json_segments():
+    """Test JSON segments format conversion."""
+    topics = [
+        TranscriptTopic(
+            id="1",
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0.0,
+            words=[
+                Word(text="Hello", start=0.0, end=1.0, speaker=0),
+                Word(text=" world.", start=1.0, end=2.0, speaker=0),
+            ],
+        ),
+        TranscriptTopic(
+            id="2",
+            title="Topic 2",
+            summary="Summary 2",
+            timestamp=2.0,
+            words=[
+                Word(text="How", start=2.0, end=3.0, speaker=1),
+                Word(text=" are", start=3.0, end=4.0, speaker=1),
+                Word(text=" you?", start=4.0, end=5.0, speaker=1),
+            ],
+        ),
+    ]
+
+    participants = [
+        TranscriptParticipant(id="1", speaker=0, name="John Smith"),
+        TranscriptParticipant(id="2", speaker=1, name="Jane Doe"),
+    ]
+
+    result = transcript_to_json_segments(topics, participants)
+
+    assert len(result) == 2
+    assert result[0].speaker == 0
+    assert result[0].speaker_name == "John Smith"
+    assert result[0].text == "Hello world."
+    assert result[0].start == 0.0
+    assert result[0].end == 2.0
+
+    assert result[1].speaker == 1
+    assert result[1].speaker_name == "Jane Doe"
+    assert result[1].text == "How are you?"
+    assert result[1].start == 2.0
+    assert result[1].end == 5.0
+
+
+@pytest.mark.asyncio
+async def test_transcript_formats_with_empty_topics():
+    """Test format conversion with empty topics list."""
+    topics = []
+    participants = []
+
+    assert transcript_to_text(topics, participants) == ""
+    assert transcript_to_text_timestamped(topics, participants) == ""
+    assert "WEBVTT" in topics_to_webvtt_named(topics, participants)
+    assert transcript_to_json_segments(topics, participants) == []
+
+
+@pytest.mark.asyncio
+async def test_transcript_formats_with_empty_words():
+    """Test format conversion with topics containing no words."""
+    topics = [
+        TranscriptTopic(
+            id="1",
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0.0,
+            words=[],
+        ),
+    ]
+    participants = []
+
+    assert transcript_to_text(topics, participants) == ""
+    assert transcript_to_text_timestamped(topics, participants) == ""
+    assert "WEBVTT" in topics_to_webvtt_named(topics, participants)
+    assert transcript_to_json_segments(topics, participants) == []
+
+
+@pytest.mark.asyncio
+async def test_transcript_formats_with_multiple_speakers():
+    """Test format conversion with multiple speaker changes."""
+    topics = [
+        TranscriptTopic(
+            id="1",
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0.0,
+            words=[
+                Word(text="Hello", start=0.0, end=1.0, speaker=0),
+                Word(text=" there.", start=1.0, end=2.0, speaker=0),
+                Word(text="Hi", start=2.0, end=3.0, speaker=1),
+                Word(text=" back.", start=3.0, end=4.0, speaker=1),
+                Word(text="Good", start=4.0, end=5.0, speaker=0),
+                Word(text=" morning.", start=5.0, end=6.0, speaker=0),
+            ],
+        ),
+    ]
+
+    participants = [
+        TranscriptParticipant(id="1", speaker=0, name="Alice"),
+        TranscriptParticipant(id="2", speaker=1, name="Bob"),
+    ]
+
+    text_result = transcript_to_text(topics, participants)
+    lines = text_result.split("\n")
+    assert len(lines) == 3
+    assert "Alice: Hello there." in lines[0]
+    assert "Bob: Hi back." in lines[1]
+    assert "Alice: Good morning." in lines[2]
+
+    json_result = transcript_to_json_segments(topics, participants)
+    assert len(json_result) == 3
+    assert json_result[0].speaker_name == "Alice"
+    assert json_result[1].speaker_name == "Bob"
+    assert json_result[2].speaker_name == "Alice"
+
+
+@pytest.mark.asyncio
+async def test_transcript_formats_with_overlapping_speakers_multitrack():
+    """Test format conversion for multitrack recordings with truly interleaved words.
+
+    Multitrack recordings have words from different speakers sorted by start time,
+    causing frequent speaker alternation. This tests the sentence-based segmentation
+    that groups each speaker's words into complete sentences.
+    """
+    # Real multitrack data: words sorted by start time, speakers interleave
+    # Alice says: "Hello there." (0.0-1.0)
+    # Bob says: "I'm good." (0.5-1.5)
+    # When sorted by time, words interleave: Hello, I'm, there., good.
+    topics = [
+        TranscriptTopic(
+            id="1",
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0.0,
+            words=[
+                Word(text="Hello ", start=0.0, end=0.5, speaker=0),
+                Word(text="I'm ", start=0.5, end=0.8, speaker=1),
+                Word(text="there.", start=0.5, end=1.0, speaker=0),
+                Word(text="good.", start=1.0, end=1.5, speaker=1),
+            ],
+        ),
+    ]
+
+    participants = [
+        TranscriptParticipant(id="1", speaker=0, name="Alice"),
+        TranscriptParticipant(id="2", speaker=1, name="Bob"),
+    ]
+
+    # With is_multitrack=True, should produce 2 segments (one per speaker sentence)
+    # not 4 segments (one per speaker change)
+    webvtt_result = topics_to_webvtt_named(topics, participants, is_multitrack=True)
+    expected_webvtt = """WEBVTT
+
+00:00:00.000 --> 00:00:01.000
+<v Alice>Hello there.
+
+00:00:00.500 --> 00:00:01.500
+<v Bob>I'm good.
+"""
+    assert webvtt_result == expected_webvtt
+
+    text_result = transcript_to_text(topics, participants, is_multitrack=True)
+    lines = text_result.split("\n")
+    assert len(lines) == 2
+    assert "Alice: Hello there." in lines[0]
+    assert "Bob: I'm good." in lines[1]
+
+    timestamped_result = transcript_to_text_timestamped(
+        topics, participants, is_multitrack=True
+    )
+    timestamped_lines = timestamped_result.split("\n")
+    assert len(timestamped_lines) == 2
+    assert "[00:00] Alice: Hello there." in timestamped_lines[0]
+    assert "[00:00] Bob: I'm good." in timestamped_lines[1]
+
+    segments = transcript_to_json_segments(topics, participants, is_multitrack=True)
+    assert len(segments) == 2
+    assert segments[0].speaker_name == "Alice"
+    assert segments[0].text == "Hello there."
+    assert segments[1].speaker_name == "Bob"
+    assert segments[1].text == "I'm good."
+
+
+@pytest.mark.asyncio
+async def test_api_transcript_format_text(client):
+    """Test GET /transcripts/{id} with transcript_format=text."""
+    response = await client.post("/transcripts", json={"name": "Test transcript"})
+    assert response.status_code == 200
+    tid = response.json()["id"]
+
+    from reflector.db.transcripts import (
+        TranscriptParticipant,
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.types import Word
+
+    transcript = await transcripts_controller.get_by_id(tid)
+
+    await transcripts_controller.update(
+        transcript,
+        {
+            "participants": [
+                TranscriptParticipant(
+                    id="1", speaker=0, name="John Smith"
+                ).model_dump(),
+                TranscriptParticipant(id="2", speaker=1, name="Jane Doe").model_dump(),
+            ]
+        },
+    )
+
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello", start=0, end=1, speaker=0),
+                Word(text=" world.", start=1, end=2, speaker=0),
+            ],
+        ),
+    )
+
+    response = await client.get(f"/transcripts/{tid}?transcript_format=text")
+    assert response.status_code == 200
+    data = response.json()
+
+    assert data["transcript_format"] == "text"
+    assert "transcript" in data
+    assert "John Smith: Hello world." in data["transcript"]
+
+
+@pytest.mark.asyncio
+async def test_api_transcript_format_text_timestamped(client):
+    """Test GET /transcripts/{id} with transcript_format=text-timestamped."""
+    response = await client.post("/transcripts", json={"name": "Test transcript"})
+    assert response.status_code == 200
+    tid = response.json()["id"]
+
+    from reflector.db.transcripts import (
+        TranscriptParticipant,
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.types import Word
+
+    transcript = await transcripts_controller.get_by_id(tid)
+
+    await transcripts_controller.update(
+        transcript,
+        {
+            "participants": [
+                TranscriptParticipant(
+                    id="1", speaker=0, name="John Smith"
+                ).model_dump(),
+            ]
+        },
+    )
+
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello", start=65, end=66, speaker=0),
+                Word(text=" world.", start=66, end=67, speaker=0),
+            ],
+        ),
+    )
+
+    response = await client.get(
+        f"/transcripts/{tid}?transcript_format=text-timestamped"
+    )
+    assert response.status_code == 200
+    data = response.json()
+
+    assert data["transcript_format"] == "text-timestamped"
+    assert "transcript" in data
+    assert "[01:05] John Smith: Hello world." in data["transcript"]
+
+
+@pytest.mark.asyncio
+async def test_api_transcript_format_webvtt_named(client):
+    """Test GET /transcripts/{id} with transcript_format=webvtt-named."""
+    response = await client.post("/transcripts", json={"name": "Test transcript"})
+    assert response.status_code == 200
+    tid = response.json()["id"]
+
+    from reflector.db.transcripts import (
+        TranscriptParticipant,
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.types import Word
+
+    transcript = await transcripts_controller.get_by_id(tid)
+
+    await transcripts_controller.update(
+        transcript,
+        {
+            "participants": [
+                TranscriptParticipant(
+                    id="1", speaker=0, name="John Smith"
+                ).model_dump(),
+            ]
+        },
+    )
+
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello", start=0, end=1, speaker=0),
+                Word(text=" world.", start=1, end=2, speaker=0),
+            ],
+        ),
+    )
+
+    response = await client.get(f"/transcripts/{tid}?transcript_format=webvtt-named")
+    assert response.status_code == 200
+    data = response.json()
+
+    assert data["transcript_format"] == "webvtt-named"
+    assert "transcript" in data
+    assert "WEBVTT" in data["transcript"]
+    assert "<v John Smith>" in data["transcript"]
+
+
+@pytest.mark.asyncio
+async def test_api_transcript_format_json(client):
+    """Test GET /transcripts/{id} with transcript_format=json."""
+    response = await client.post("/transcripts", json={"name": "Test transcript"})
+    assert response.status_code == 200
+    tid = response.json()["id"]
+
+    from reflector.db.transcripts import (
+        TranscriptParticipant,
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.types import Word
+
+    transcript = await transcripts_controller.get_by_id(tid)
+
+    await transcripts_controller.update(
+        transcript,
+        {
+            "participants": [
+                TranscriptParticipant(
+                    id="1", speaker=0, name="John Smith"
+                ).model_dump(),
+            ]
+        },
+    )
+
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello", start=0, end=1, speaker=0),
+                Word(text=" world.", start=1, end=2, speaker=0),
+            ],
+        ),
+    )
+
+    response = await client.get(f"/transcripts/{tid}?transcript_format=json")
+    assert response.status_code == 200
+    data = response.json()
+
+    assert data["transcript_format"] == "json"
+    assert "transcript" in data
+    assert isinstance(data["transcript"], list)
+    assert len(data["transcript"]) == 1
+    assert data["transcript"][0]["speaker"] == 0
+    assert data["transcript"][0]["speaker_name"] == "John Smith"
+    assert data["transcript"][0]["text"] == "Hello world."
+
+
+@pytest.mark.asyncio
+async def test_api_transcript_format_default_is_text(client):
+    """Test GET /transcripts/{id} defaults to text format."""
+    response = await client.post("/transcripts", json={"name": "Test transcript"})
+    assert response.status_code == 200
+    tid = response.json()["id"]
+
+    from reflector.db.transcripts import TranscriptTopic, transcripts_controller
+    from reflector.processors.types import Word
+
+    transcript = await transcripts_controller.get_by_id(tid)
+
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello", start=0, end=1, speaker=0),
+            ],
+        ),
+    )
+
+    response = await client.get(f"/transcripts/{tid}")
+    assert response.status_code == 200
+    data = response.json()
+
+    assert data["transcript_format"] == "text"
+    assert "transcript" in data
+
+
+@pytest.mark.asyncio
+async def test_api_topics_endpoint_multitrack_segmentation(client):
+    """Test GET /transcripts/{id}/topics uses sentence-based segmentation for multitrack.
+
+    This tests the fix for TASKS2.md - ensuring /topics endpoints correctly detect
+    multitrack recordings and use sentence-based segmentation instead of fragmenting
+    on every speaker change.
+    """
+    from datetime import datetime, timezone
+
+    from reflector.db.recordings import Recording, recordings_controller
+    from reflector.db.transcripts import (
+        TranscriptParticipant,
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.types import Word
+
+    # Create a multitrack recording (has track_keys)
+    recording = Recording(
+        bucket_name="test-bucket",
+        object_key="test-key",
+        recorded_at=datetime.now(timezone.utc),
+        track_keys=["track1.webm", "track2.webm"],  # This makes it multitrack
+    )
+    await recordings_controller.create(recording)
+
+    # Create transcript linked to the recording
+    transcript = await transcripts_controller.add(
+        name="Multitrack Test",
+        source_kind="file",
+        recording_id=recording.id,
+    )
+
+    await transcripts_controller.update(
+        transcript,
+        {
+            "participants": [
+                TranscriptParticipant(id="1", speaker=0, name="Alice").model_dump(),
+                TranscriptParticipant(id="2", speaker=1, name="Bob").model_dump(),
+            ]
+        },
+    )
+
+    # Add interleaved words (as they appear in real multitrack data)
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello ", start=0.0, end=0.5, speaker=0),
+                Word(text="I'm ", start=0.5, end=0.8, speaker=1),
+                Word(text="there.", start=0.5, end=1.0, speaker=0),
+                Word(text="good.", start=1.0, end=1.5, speaker=1),
+            ],
+        ),
+    )
+
+    # Test /topics endpoint
+    response = await client.get(f"/transcripts/{transcript.id}/topics")
+    assert response.status_code == 200
+    data = response.json()
+
+    assert len(data) == 1
+    topic = data[0]
+
+    # Key assertion: multitrack should produce 2 segments (one per speaker sentence)
+    # Not 4 segments (one per speaker change)
+    assert len(topic["segments"]) == 2
+
+    # Check content
+    segment_texts = [s["text"] for s in topic["segments"]]
+    assert "Hello there." in segment_texts
+    assert "I'm good." in segment_texts
+
+
+@pytest.mark.asyncio
+async def test_api_topics_endpoint_non_multitrack_segmentation(client):
+    """Test GET /transcripts/{id}/topics uses default segmentation for non-multitrack.
+
+    Ensures backward compatibility - transcripts without multitrack recordings
+    should continue using the default speaker-change-based segmentation.
+    """
+    from reflector.db.transcripts import (
+        TranscriptParticipant,
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.types import Word
+
+    # Create transcript WITHOUT recording (defaulted as not multitrack) TODO better heuristic
+    response = await client.post("/transcripts", json={"name": "Test transcript"})
+    assert response.status_code == 200
+    tid = response.json()["id"]
+
+    transcript = await transcripts_controller.get_by_id(tid)
+
+    await transcripts_controller.update(
+        transcript,
+        {
+            "participants": [
+                TranscriptParticipant(id="1", speaker=0, name="Alice").model_dump(),
+                TranscriptParticipant(id="2", speaker=1, name="Bob").model_dump(),
+            ]
+        },
+    )
+
+    # Add interleaved words
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello ", start=0.0, end=0.5, speaker=0),
+                Word(text="I'm ", start=0.5, end=0.8, speaker=1),
+                Word(text="there.", start=0.5, end=1.0, speaker=0),
+                Word(text="good.", start=1.0, end=1.5, speaker=1),
+            ],
+        ),
+    )
+
+    # Test /topics endpoint
+    response = await client.get(f"/transcripts/{tid}/topics")
+    assert response.status_code == 200
+    data = response.json()
+
+    assert len(data) == 1
+    topic = data[0]
+
+    # Non-multitrack: should produce 4 segments (one per speaker change)
+    assert len(topic["segments"]) == 4
+
+
+@pytest.mark.asyncio
+async def test_api_topics_with_words_endpoint_multitrack(client):
+    """Test GET /transcripts/{id}/topics/with-words uses multitrack segmentation."""
+    from datetime import datetime, timezone
+
+    from reflector.db.recordings import Recording, recordings_controller
+    from reflector.db.transcripts import (
+        TranscriptParticipant,
+        TranscriptTopic,
+        transcripts_controller,
+    )
+    from reflector.processors.types import Word
+
+    # Create multitrack recording
+    recording = Recording(
+        bucket_name="test-bucket",
+        object_key="test-key-2",
+        recorded_at=datetime.now(timezone.utc),
+        track_keys=["track1.webm", "track2.webm"],
+    )
+    await recordings_controller.create(recording)
+
+    transcript = await transcripts_controller.add(
+        name="Multitrack Test 2",
+        source_kind="file",
+        recording_id=recording.id,
+    )
+
+    await transcripts_controller.update(
+        transcript,
+        {
+            "participants": [
+                TranscriptParticipant(id="1", speaker=0, name="Alice").model_dump(),
+                TranscriptParticipant(id="2", speaker=1, name="Bob").model_dump(),
+            ]
+        },
+    )
+
+    await transcripts_controller.upsert_topic(
+        transcript,
+        TranscriptTopic(
+            title="Topic 1",
+            summary="Summary 1",
+            timestamp=0,
+            words=[
+                Word(text="Hello ", start=0.0, end=0.5, speaker=0),
+                Word(text="I'm ", start=0.5, end=0.8, speaker=1),
+                Word(text="there.", start=0.5, end=1.0, speaker=0),
+                Word(text="good.", start=1.0, end=1.5, speaker=1),
+            ],
+        ),
+    )
+
+    response = await client.get(f"/transcripts/{transcript.id}/topics/with-words")
+    assert response.status_code == 200
+    data = response.json()
+
+    assert len(data) == 1
+    topic = data[0]
+
+    # Should have 2 segments (multitrack sentence-based)
+    assert len(topic["segments"]) == 2
+    # Should also have words field
+    assert "words" in topic
+    assert len(topic["words"]) == 4

www/app/(app)/transcripts/shareCopy.tsx

@@ -1,14 +1,16 @@
 import { useState } from "react";
-import type { components } from "../../reflector-api";
-type GetTranscript = components["schemas"]["GetTranscript"];
+import type { components, operations } from "../../reflector-api";
+type GetTranscriptWithParticipants =
+  components["schemas"]["GetTranscriptWithParticipants"];
 type GetTranscriptTopic = components["schemas"]["GetTranscriptTopic"];
-import { Button, BoxProps, Box } from "@chakra-ui/react";
-import { buildTranscriptWithTopics } from "./buildTranscriptWithTopics";
-import { useTranscriptParticipants } from "../../lib/apiHooks";
+import { Button, BoxProps, Box, Menu, Text } from "@chakra-ui/react";
+import { LuChevronDown } from "react-icons/lu";
+import { client } from "../../lib/apiClient";
+import { toaster } from "../../components/ui/toaster";
 
 type ShareCopyProps = {
   finalSummaryElement: HTMLDivElement | null;
-  transcript: GetTranscript;
+  transcript: GetTranscriptWithParticipants;
   topics: GetTranscriptTopic[];
 };
 
@@ -20,11 +22,33 @@ export default function ShareCopy({
 }: ShareCopyProps & BoxProps) {
   const [isCopiedSummary, setIsCopiedSummary] = useState(false);
   const [isCopiedTranscript, setIsCopiedTranscript] = useState(false);
-  const participantsQuery = useTranscriptParticipants(transcript?.id || null);
+  const [isCopying, setIsCopying] = useState(false);
+
+  type ApiTranscriptFormat = NonNullable<
+    operations["v1_transcript_get"]["parameters"]["query"]
+  >["transcript_format"];
+  const TRANSCRIPT_FORMATS = [
+    "text",
+    "text-timestamped",
+    "webvtt-named",
+    "json",
+  ] as const satisfies ApiTranscriptFormat[];
+  type TranscriptFormat = (typeof TRANSCRIPT_FORMATS)[number];
+
+  const TRANSCRIPT_FORMAT_LABELS: { [k in TranscriptFormat]: string } = {
+    text: "Plain text",
+    "text-timestamped": "Text + timestamps",
+    "webvtt-named": "WebVTT (named)",
+    json: "JSON",
+  };
+
+  const formatOptions = TRANSCRIPT_FORMATS.map((f) => ({
+    value: f,
+    label: TRANSCRIPT_FORMAT_LABELS[f],
+  }));
 
   const onCopySummaryClick = () => {
     const text_to_copy = finalSummaryElement?.innerText;
-
     if (text_to_copy) {
       navigator.clipboard.writeText(text_to_copy).then(() => {
         setIsCopiedSummary(true);
@@ -34,27 +58,91 @@ export default function ShareCopy({
     }
   };
 
-  const onCopyTranscriptClick = () => {
-    const text_to_copy =
-      buildTranscriptWithTopics(
-        topics || [],
-        participantsQuery?.data || null,
-        transcript?.title || null,
-      ) || "";
-
-    text_to_copy &&
-      navigator.clipboard.writeText(text_to_copy).then(() => {
-        setIsCopiedTranscript(true);
-        // Reset the copied state after 2 seconds
-        setTimeout(() => setIsCopiedTranscript(false), 2000);
+  const onCopyTranscriptFormatClick = async (format: TranscriptFormat) => {
+    try {
+      setIsCopying(true);
+      const { data, error } = await client.GET(
+        "/v1/transcripts/{transcript_id}",
+        {
+          params: {
+            path: { transcript_id: transcript.id },
+            query: { transcript_format: format },
+          },
+        },
+      );
+      if (error) {
+        console.error("Failed to copy transcript:", error);
+        toaster.create({
+          duration: 3000,
+          render: () => (
+            <Box bg="red.500" color="white" px={4} py={3} borderRadius="md">
+              <Text fontWeight="bold">Error</Text>
+              <Text fontSize="sm">Failed to fetch transcript</Text>
+            </Box>
+          ),
         });
+        return;
+      }
+
+      const copiedText =
+        format === "json"
+          ? JSON.stringify(data?.transcript ?? {}, null, 2)
+          : String(data?.transcript ?? "");
+
+      if (copiedText) {
+        await navigator.clipboard.writeText(copiedText);
+        setIsCopiedTranscript(true);
+        setTimeout(() => setIsCopiedTranscript(false), 2000);
+      }
+    } catch (e) {
+      console.error("Failed to copy transcript:", e);
+      toaster.create({
+        duration: 3000,
+        render: () => (
+          <Box bg="red.500" color="white" px={4} py={3} borderRadius="md">
+            <Text fontWeight="bold">Error</Text>
+            <Text fontSize="sm">Failed to copy transcript</Text>
+          </Box>
+        ),
+      });
+    } finally {
+      setIsCopying(false);
+    }
   };
 
   return (
     <Box {...boxProps}>
-      <Button onClick={onCopyTranscriptClick} mr={2} variant="subtle">
+      <Menu.Root
+        closeOnSelect={true}
+        lazyMount={true}
+        positioning={{ gutter: 4 }}
+      >
+        <Menu.Trigger asChild>
+          <Button
+            mr={2}
+            variant="subtle"
+            loading={isCopying}
+            loadingText="Copying..."
+          >
             {isCopiedTranscript ? "Copied!" : "Copy Transcript"}
+            <LuChevronDown style={{ marginLeft: 6 }} />
           </Button>
+        </Menu.Trigger>
+        <Menu.Positioner>
+          <Menu.Content>
+            {formatOptions.map((opt) => (
+              <Menu.Item
+                key={opt.value}
+                value={opt.value}
+                _hover={{ backgroundColor: "gray.100" }}
+                onClick={() => onCopyTranscriptFormatClick(opt.value)}
+              >
+                {opt.label}
+              </Menu.Item>
+            ))}
+          </Menu.Content>
+        </Menu.Positioner>
+      </Menu.Root>
       <Button onClick={onCopySummaryClick} variant="subtle">
         {isCopiedSummary ? "Copied!" : "Copy Summary"}
       </Button>

www/app/lib/authBackend.ts

@@ -32,6 +32,11 @@ async function getUserId(accessToken: string): Promise<string | null> {
     });
 
     if (!response.ok) {
+      try {
+        console.error(await response.text());
+      } catch (e) {
+        console.error("Failed to parse error response", e);
+      }
       return null;
     }
 

www/app/reflector-api.d.ts

@@ -696,7 +696,7 @@ export interface paths {
     patch?: never;
     trace?: never;
   };
-  "/v1/webhook": {
+  "/v1/daily/webhook": {
     parameters: {
       query?: never;
       header?: never;
@@ -708,6 +708,27 @@ export interface paths {
     /**
      * Webhook
      * @description Handle Daily webhook events.
+     *
+     *     Example webhook payload:
+     *     {
+     *       "version": "1.0.0",
+     *       "type": "recording.ready-to-download",
+     *       "id": "rec-rtd-c3df927c-f738-4471-a2b7-066fa7e95a6b-1692124192",
+     *       "payload": {
+     *         "recording_id": "08fa0b24-9220-44c5-846c-3f116cf8e738",
+     *         "room_name": "Xcm97xRZ08b2dePKb78g",
+     *         "start_ts": 1692124183,
+     *         "status": "finished",
+     *         "max_participants": 1,
+     *         "duration": 9,
+     *         "share_token": "ntDCL5k98Ulq", #gitleaks:allow
+     *         "s3_key": "api-test-1j8fizhzd30c/Xcm97xRZ08b2dePKb78g/1692124183028"
+     *       },
+     *       "event_ts": 1692124192
+     *     }
+     *
+     *     Daily.co circuit-breaker: After 3+ failed responses (4xx/5xx), webhook
+     *     state→FAILED, stops sending events. Reset: scripts/recreate_daily_webhook.py
      */
     post: operations["v1_webhook"];
     delete?: never;
@@ -899,81 +920,11 @@ export interface components {
       target_language: string;
       source_kind?: components["schemas"]["SourceKind"] | null;
     };
-    /**
-     * DailyWebhookEvent
-     * @description Daily webhook event structure.
-     */
-    DailyWebhookEvent: {
-      /** Type */
-      type: string;
-      /** Id */
-      id: string;
-      /** Ts */
-      ts: number;
-      /** Data */
-      data: {
-        [key: string]: unknown;
-      };
-    };
     /** DeletionStatus */
     DeletionStatus: {
       /** Status */
       status: string;
     };
-    /** GetTranscript */
-    GetTranscript: {
-      /** Id */
-      id: string;
-      /** User Id */
-      user_id: string | null;
-      /** Name */
-      name: string;
-      /**
-       * Status
-       * @enum {string}
-       */
-      status:
-        | "idle"
-        | "uploaded"
-        | "recording"
-        | "processing"
-        | "error"
-        | "ended";
-      /** Locked */
-      locked: boolean;
-      /** Duration */
-      duration: number;
-      /** Title */
-      title: string | null;
-      /** Short Summary */
-      short_summary: string | null;
-      /** Long Summary */
-      long_summary: string | null;
-      /** Created At */
-      created_at: string;
-      /**
-       * Share Mode
-       * @default private
-       */
-      share_mode: string;
-      /** Source Language */
-      source_language: string | null;
-      /** Target Language */
-      target_language: string | null;
-      /** Reviewed */
-      reviewed: boolean;
-      /** Meeting Id */
-      meeting_id: string | null;
-      source_kind: components["schemas"]["SourceKind"];
-      /** Room Id */
-      room_id?: string | null;
-      /** Room Name */
-      room_name?: string | null;
-      /** Audio Deleted */
-      audio_deleted?: boolean | null;
-      /** Participants */
-      participants: components["schemas"]["TranscriptParticipant"][] | null;
-    };
     /** GetTranscriptMinimal */
     GetTranscriptMinimal: {
       /** Id */
@@ -1105,6 +1056,345 @@ export interface components {
        */
       words_per_speaker: components["schemas"]["SpeakerWords"][];
     };
+    /**
+     * GetTranscriptWithJSON
+     * @description Transcript response as structured JSON segments.
+     *
+     *     Format: Array of segment objects with speaker info, text, and timing.
+     *     Example:
+     *         [
+     *             {
+     *                 "speaker": 0,
+     *                 "speaker_name": "John Smith",
+     *                 "text": "Hello everyone",
+     *                 "start": 0.0,
+     *                 "end": 5.0
+     *             }
+     *         ]
+     */
+    GetTranscriptWithJSON: {
+      /** Id */
+      id: string;
+      /** User Id */
+      user_id: string | null;
+      /** Name */
+      name: string;
+      /**
+       * Status
+       * @enum {string}
+       */
+      status:
+        | "idle"
+        | "uploaded"
+        | "recording"
+        | "processing"
+        | "error"
+        | "ended";
+      /** Locked */
+      locked: boolean;
+      /** Duration */
+      duration: number;
+      /** Title */
+      title: string | null;
+      /** Short Summary */
+      short_summary: string | null;
+      /** Long Summary */
+      long_summary: string | null;
+      /** Created At */
+      created_at: string;
+      /**
+       * Share Mode
+       * @default private
+       */
+      share_mode: string;
+      /** Source Language */
+      source_language: string | null;
+      /** Target Language */
+      target_language: string | null;
+      /** Reviewed */
+      reviewed: boolean;
+      /** Meeting Id */
+      meeting_id: string | null;
+      source_kind: components["schemas"]["SourceKind"];
+      /** Room Id */
+      room_id?: string | null;
+      /** Room Name */
+      room_name?: string | null;
+      /** Audio Deleted */
+      audio_deleted?: boolean | null;
+      /** Participants */
+      participants: components["schemas"]["TranscriptParticipant"][] | null;
+      /**
+       * @description discriminator enum property added by openapi-typescript
+       * @enum {string}
+       */
+      transcript_format: "json";
+      /** Transcript */
+      transcript: components["schemas"]["TranscriptSegment"][];
+    };
+    /** GetTranscriptWithParticipants */
+    GetTranscriptWithParticipants: {
+      /** Id */
+      id: string;
+      /** User Id */
+      user_id: string | null;
+      /** Name */
+      name: string;
+      /**
+       * Status
+       * @enum {string}
+       */
+      status:
+        | "idle"
+        | "uploaded"
+        | "recording"
+        | "processing"
+        | "error"
+        | "ended";
+      /** Locked */
+      locked: boolean;
+      /** Duration */
+      duration: number;
+      /** Title */
+      title: string | null;
+      /** Short Summary */
+      short_summary: string | null;
+      /** Long Summary */
+      long_summary: string | null;
+      /** Created At */
+      created_at: string;
+      /**
+       * Share Mode
+       * @default private
+       */
+      share_mode: string;
+      /** Source Language */
+      source_language: string | null;
+      /** Target Language */
+      target_language: string | null;
+      /** Reviewed */
+      reviewed: boolean;
+      /** Meeting Id */
+      meeting_id: string | null;
+      source_kind: components["schemas"]["SourceKind"];
+      /** Room Id */
+      room_id?: string | null;
+      /** Room Name */
+      room_name?: string | null;
+      /** Audio Deleted */
+      audio_deleted?: boolean | null;
+      /** Participants */
+      participants: components["schemas"]["TranscriptParticipant"][] | null;
+    };
+    /**
+     * GetTranscriptWithText
+     * @description Transcript response with plain text format.
+     *
+     *     Format: Speaker names followed by their dialogue, one line per segment.
+     *     Example:
+     *         John Smith: Hello everyone
+     *         Jane Doe: Hi there
+     */
+    GetTranscriptWithText: {
+      /** Id */
+      id: string;
+      /** User Id */
+      user_id: string | null;
+      /** Name */
+      name: string;
+      /**
+       * Status
+       * @enum {string}
+       */
+      status:
+        | "idle"
+        | "uploaded"
+        | "recording"
+        | "processing"
+        | "error"
+        | "ended";
+      /** Locked */
+      locked: boolean;
+      /** Duration */
+      duration: number;
+      /** Title */
+      title: string | null;
+      /** Short Summary */
+      short_summary: string | null;
+      /** Long Summary */
+      long_summary: string | null;
+      /** Created At */
+      created_at: string;
+      /**
+       * Share Mode
+       * @default private
+       */
+      share_mode: string;
+      /** Source Language */
+      source_language: string | null;
+      /** Target Language */
+      target_language: string | null;
+      /** Reviewed */
+      reviewed: boolean;
+      /** Meeting Id */
+      meeting_id: string | null;
+      source_kind: components["schemas"]["SourceKind"];
+      /** Room Id */
+      room_id?: string | null;
+      /** Room Name */
+      room_name?: string | null;
+      /** Audio Deleted */
+      audio_deleted?: boolean | null;
+      /** Participants */
+      participants: components["schemas"]["TranscriptParticipant"][] | null;
+      /**
+       * @description discriminator enum property added by openapi-typescript
+       * @enum {string}
+       */
+      transcript_format: "text";
+      /** Transcript */
+      transcript: string;
+    };
+    /**
+     * GetTranscriptWithTextTimestamped
+     * @description Transcript response with timestamped text format.
+     *
+     *     Format: [MM:SS] timestamp prefix before each speaker and dialogue.
+     *     Example:
+     *         [00:00] John Smith: Hello everyone
+     *         [00:05] Jane Doe: Hi there
+     */
+    GetTranscriptWithTextTimestamped: {
+      /** Id */
+      id: string;
+      /** User Id */
+      user_id: string | null;
+      /** Name */
+      name: string;
+      /**
+       * Status
+       * @enum {string}
+       */
+      status:
+        | "idle"
+        | "uploaded"
+        | "recording"
+        | "processing"
+        | "error"
+        | "ended";
+      /** Locked */
+      locked: boolean;
+      /** Duration */
+      duration: number;
+      /** Title */
+      title: string | null;
+      /** Short Summary */
+      short_summary: string | null;
+      /** Long Summary */
+      long_summary: string | null;
+      /** Created At */
+      created_at: string;
+      /**
+       * Share Mode
+       * @default private
+       */
+      share_mode: string;
+      /** Source Language */
+      source_language: string | null;
+      /** Target Language */
+      target_language: string | null;
+      /** Reviewed */
+      reviewed: boolean;
+      /** Meeting Id */
+      meeting_id: string | null;
+      source_kind: components["schemas"]["SourceKind"];
+      /** Room Id */
+      room_id?: string | null;
+      /** Room Name */
+      room_name?: string | null;
+      /** Audio Deleted */
+      audio_deleted?: boolean | null;
+      /** Participants */
+      participants: components["schemas"]["TranscriptParticipant"][] | null;
+      /**
+       * @description discriminator enum property added by openapi-typescript
+       * @enum {string}
+       */
+      transcript_format: "text-timestamped";
+      /** Transcript */
+      transcript: string;
+    };
+    /**
+     * GetTranscriptWithWebVTTNamed
+     * @description Transcript response in WebVTT subtitle format with participant names.
+     *
+     *     Format: Standard WebVTT with voice tags using participant names.
+     *     Example:
+     *         WEBVTT
+     *
+     *         00:00:00.000 --> 00:00:05.000
+     *         <v John Smith>Hello everyone
+     */
+    GetTranscriptWithWebVTTNamed: {
+      /** Id */
+      id: string;
+      /** User Id */
+      user_id: string | null;
+      /** Name */
+      name: string;
+      /**
+       * Status
+       * @enum {string}
+       */
+      status:
+        | "idle"
+        | "uploaded"
+        | "recording"
+        | "processing"
+        | "error"
+        | "ended";
+      /** Locked */
+      locked: boolean;
+      /** Duration */
+      duration: number;
+      /** Title */
+      title: string | null;
+      /** Short Summary */
+      short_summary: string | null;
+      /** Long Summary */
+      long_summary: string | null;
+      /** Created At */
+      created_at: string;
+      /**
+       * Share Mode
+       * @default private
+       */
+      share_mode: string;
+      /** Source Language */
+      source_language: string | null;
+      /** Target Language */
+      target_language: string | null;
+      /** Reviewed */
+      reviewed: boolean;
+      /** Meeting Id */
+      meeting_id: string | null;
+      source_kind: components["schemas"]["SourceKind"];
+      /** Room Id */
+      room_id?: string | null;
+      /** Room Name */
+      room_name?: string | null;
+      /** Audio Deleted */
+      audio_deleted?: boolean | null;
+      /** Participants */
+      participants: components["schemas"]["TranscriptParticipant"][] | null;
+      /**
+       * @description discriminator enum property added by openapi-typescript
+       * @enum {string}
+       */
+      transcript_format: "webvtt-named";
+      /** Transcript */
+      transcript: string;
+    };
     /** HTTPValidationError */
     HTTPValidationError: {
       /** Detail */
@@ -1233,7 +1523,6 @@ export interface components {
       } | null;
       /**
        * Platform
-       * @default whereby
        * @enum {string}
        */
       platform: "whereby" | "daily";
@@ -1325,7 +1614,6 @@ export interface components {
       ics_last_etag?: string | null;
       /**
        * Platform
-       * @default whereby
        * @enum {string}
        */
       platform: "whereby" | "daily";
@@ -1377,7 +1665,6 @@ export interface components {
       ics_last_etag?: string | null;
       /**
        * Platform
-       * @default whereby
        * @enum {string}
        */
       platform: "whereby" | "daily";
@@ -1523,6 +1810,24 @@ export interface components {
       speaker: number | null;
       /** Name */
       name: string;
+      /** User Id */
+      user_id?: string | null;
+    };
+    /**
+     * TranscriptSegment
+     * @description A single transcript segment with speaker and timing information.
+     */
+    TranscriptSegment: {
+      /** Speaker */
+      speaker: number;
+      /** Speaker Name */
+      speaker_name: string;
+      /** Text */
+      text: string;
+      /** Start */
+      start: number;
+      /** End */
+      end: number;
     };
     /** UpdateParticipant */
     UpdateParticipant: {
@@ -2311,7 +2616,7 @@ export interface operations {
           [name: string]: unknown;
         };
         content: {
-          "application/json": components["schemas"]["GetTranscript"];
+          "application/json": components["schemas"]["GetTranscriptWithParticipants"];
         };
       };
       /** @description Validation Error */
@@ -2369,7 +2674,13 @@ export interface operations {
   };
   v1_transcript_get: {
     parameters: {
-      query?: never;
+      query?: {
+        transcript_format?:
+          | "text"
+          | "text-timestamped"
+          | "webvtt-named"
+          | "json";
+      };
       header?: never;
       path: {
         transcript_id: string;
@@ -2384,7 +2695,11 @@ export interface operations {
           [name: string]: unknown;
         };
         content: {
-          "application/json": components["schemas"]["GetTranscript"];
+          "application/json":
+            | components["schemas"]["GetTranscriptWithText"]
+            | components["schemas"]["GetTranscriptWithTextTimestamped"]
+            | components["schemas"]["GetTranscriptWithWebVTTNamed"]
+            | components["schemas"]["GetTranscriptWithJSON"];
         };
       };
       /** @description Validation Error */
@@ -2450,7 +2765,7 @@ export interface operations {
           [name: string]: unknown;
         };
         content: {
-          "application/json": components["schemas"]["GetTranscript"];
+          "application/json": components["schemas"]["GetTranscriptWithParticipants"];
         };
       };
       /** @description Validation Error */
@@ -3256,11 +3571,7 @@ export interface operations {
       path?: never;
       cookie?: never;
     };
-    requestBody: {
-      content: {
-        "application/json": components["schemas"]["DailyWebhookEvent"];
-      };
-    };
+    requestBody?: never;
     responses: {
       /** @description Successful Response */
       200: {
@@ -3271,15 +3582,6 @@ export interface operations {
           "application/json": unknown;
         };
       };
-      /** @description Validation Error */
-      422: {
-        headers: {
-          [name: string]: unknown;
-        };
-        content: {
-          "application/json": components["schemas"]["HTTPValidationError"];
-        };
-      };
     };
   };
 }