server: prevent storing audio for transcription unless wanted

Closes #145

server/reflector/processors/audio_merge.py

@@ -1,6 +1,8 @@
 from reflector.processors.base import Processor
 from reflector.processors.types import AudioFile
-from pathlib import Path
+from time import monotonic_ns
+from uuid import uuid4
+import io
 import wave
 import av
 
@@ -24,12 +26,9 @@ class AudioMergeProcessor(Processor):
         sample_width = frame.format.bytes
 
         # create audio file
-        from time import monotonic_ns
-        from uuid import uuid4
-
         uu = uuid4().hex
-        path = Path(f"audio_{monotonic_ns()}_{uu}.wav")
+        fd = io.BytesIO()
-        with wave.open(path.as_posix(), "wb") as wf:
+        with wave.open(fd, "wb") as wf:
             wf.setnchannels(channels)
             wf.setsampwidth(sample_width)
             wf.setframerate(sample_rate)
@@ -38,7 +37,8 @@ class AudioMergeProcessor(Processor):
 
         # emit audio file
         audiofile = AudioFile(
-            path=path,
+            name=f"{monotonic_ns()}-{uu}.wav",
+            fd=fd,
             sample_rate=sample_rate,
             channels=channels,
             sample_width=sample_width,

server/reflector/processors/audio_transcript_modal.py

@@ -48,9 +48,9 @@ class AudioTranscriptModalProcessor(AudioTranscriptProcessor):
 
     async def _transcript(self, data: AudioFile):
         async with httpx.AsyncClient() as client:
-            self.logger.debug(f"Try to transcribe audio {data.path.name}")
+            self.logger.debug(f"Try to transcribe audio {data.name}")
             files = {
-                "file": (data.path.name, data.path.open("rb")),
+                "file": (data.name, data.fd),
             }
             response = await retry(client.post)(
                 self.transcript_url,

server/reflector/processors/types.py

@@ -1,16 +1,41 @@
-from pydantic import BaseModel
+from pydantic import BaseModel, PrivateAttr
 from pathlib import Path
+import tempfile
+import io
 
 
 class AudioFile(BaseModel):
-    path: Path
+    name: str
     sample_rate: int
     channels: int
     sample_width: int
     timestamp: float = 0.0
 
+    _fd: io.BytesIO = PrivateAttr(None)
+    _path: Path = PrivateAttr(None)
+
+    def __init__(self, fd, **kwargs):
+        super().__init__(**kwargs)
+        self._fd = fd
+
+    @property
+    def fd(self):
+        self._fd.seek(0)
+        return self._fd
+
+    @property
+    def path(self):
+        if self._path is None:
+            # write down to disk
+            filename = tempfile.NamedTemporaryFile(suffix=".wav", delete=False).name
+            self._path = Path(filename)
+            with self._path.open("wb") as f:
+                f.write(self._fd.getbuffer())
+        return self._path
+
     def release(self):
-        self.path.unlink()
+        if self._path:
+            self._path.unlink()
 
 
 class Word(BaseModel):