diff --git a/.gitleaksignore b/.gitleaksignore
index a00500e1..8eb80bd5 100644
--- a/.gitleaksignore
+++ b/.gitleaksignore
@@ -1,3 +1,5 @@
 b9d891d3424f371642cb032ecfd0e2564470a72c:server/tests/test_transcripts_recording_deletion.py:generic-api-key:15
 docs/docs/installation/auth-setup.md:curl-auth-header:250
 docs/docs/installation/daily-setup.md:curl-auth-header:277
+gpu/self_hosted/DEV_SETUP.md:curl-auth-header:74
+gpu/self_hosted/DEV_SETUP.md:curl-auth-header:83
diff --git a/docker-compose.prod.yml b/docker-compose.prod.yml
index b1f968ed..45ff4402 100644
--- a/docker-compose.prod.yml
+++ b/docker-compose.prod.yml
@@ -2,7 +2,7 @@
 # Usage: docker compose -f docker-compose.prod.yml up -d
 #
 # Prerequisites:
-# 1. Copy env.example to .env and configure for both server/ and www/
+# 1. Copy .env.example to .env and configure for both server/ and www/
 # 2. Copy Caddyfile.example to Caddyfile and edit with your domains
 # 3. Deploy Modal GPU functions (see gpu/modal_deployments/deploy-all.sh)
 
diff --git a/docs/TODO.md b/docs/TODO.md
index 1c03f6eb..5498a767 100644
--- a/docs/TODO.md
+++ b/docs/TODO.md
@@ -84,6 +84,7 @@ Please provide specific values for:
   - Exact UDP port range used (e.g., 10000-20000)
   - STUN server configuration (if any)
   - ICE candidate gathering timeout
+  - https://docs.daily.co/guides/privacy-and-security/corporate-firewalls-nats-allowed-ip-list
 
 - [ ] **Worker Configuration**
   - Default Celery worker count
diff --git a/docs/docs/installation/overview.md b/docs/docs/installation/overview.md
index 0f1a2e92..6813e989 100644
--- a/docs/docs/installation/overview.md
+++ b/docs/docs/installation/overview.md
@@ -9,11 +9,17 @@ This guide walks you through deploying Reflector from scratch. Follow these step
 
 ## What You'll Set Up
 
-```
-User --> Caddy (auto-SSL) --> Frontend (Next.js)
-                         --> Backend (FastAPI) --> PostgreSQL
-                                               --> Redis
-                                               --> Celery Workers --> Modal.com GPU
+```mermaid
+flowchart LR
+    User --> Caddy["Caddy (auto-SSL)"]
+    Caddy --> Frontend["Frontend (Next.js)"]
+    Caddy --> Backend["Backend (FastAPI)"]
+    Backend --> PostgreSQL
+    Backend --> Redis
+    Backend --> Workers["Celery Workers"]
+    Workers --> PostgreSQL
+    Workers --> Redis
+    Workers --> GPU["GPU Processing<br/>(Modal.com OR Self-hosted)"]
 ```
 
 ## Prerequisites
@@ -22,7 +28,9 @@ Before starting, you need:
 
 - [ ] **Production server** - Ubuntu 22.04+, 4+ cores, 8GB+ RAM, public IP
 - [ ] **Two domain names** - e.g., `app.example.com` (frontend) and `api.example.com` (backend)
-- [ ] **Modal.com account** - Free tier at https://modal.com
+- [ ] **GPU processing** - Choose one:
+  - Modal.com account (free tier at https://modal.com), OR
+  - GPU server with NVIDIA GPU (8GB+ VRAM)
 - [ ] **HuggingFace account** - Free at https://huggingface.co
 - [ ] **OpenAI API key** - For summaries and topic detection at https://platform.openai.com/account/api-keys
 
@@ -52,13 +60,24 @@ dig api.example.com +short
 
 ---
 
-## Step 2: Deploy Modal GPU Functions
+## Step 2: Deploy GPU Processing
+
+Reflector requires GPU processing for transcription (Whisper) and speaker diarization (Pyannote). Choose one option:
+
+| | **Modal.com (Cloud)** | **Self-Hosted GPU** |
+|---|---|---|
+| **Best for** | No GPU hardware, zero maintenance | Own GPU server, full control |
+| **Pricing** | Pay-per-use (~$0.01-0.10/min audio) | Fixed infrastructure cost |
+| **Setup** | Run from laptop (browser auth) | Run on GPU server |
+| **Scaling** | Automatic | Manual |
+
+### Option A: Modal.com (Serverless Cloud GPU)
 
 **Location: YOUR LOCAL COMPUTER (laptop/desktop)**
 
 Modal requires browser authentication, so this runs locally - not on your server.
 
-### Accept HuggingFace Licenses
+#### Accept HuggingFace Licenses
 
 Visit both pages and click "Accept":
 - https://huggingface.co/pyannote/speaker-diarization-3.1
@@ -66,7 +85,7 @@ Visit both pages and click "Accept":
 
 Then generate a token at https://huggingface.co/settings/tokens
 
-### Deploy to Modal
+#### Deploy to Modal
 
 ```bash
 pip install modal
@@ -77,10 +96,26 @@ cd reflector/gpu/modal_deployments
 ./deploy-all.sh --hf-token YOUR_HUGGINGFACE_TOKEN
 ```
 
-**Save the output** - copy the configuration block, you'll need it for Step 5.
+**Save the output** - copy the configuration block, you'll need it for Step 4.
 
 See [Modal Setup](./modal-setup) for troubleshooting and details.
 
+### Option B: Self-Hosted GPU
+
+**Location: YOUR GPU SERVER**
+
+Requires: NVIDIA GPU with 8GB+ VRAM, Ubuntu 22.04+, 40-50GB disk (Docker) or 25-30GB (Systemd).
+
+See [Self-Hosted GPU Setup](./self-hosted-gpu-setup) for complete instructions. Quick summary:
+
+1. Install NVIDIA drivers and Docker (or uv for systemd)
+2. Clone repository: `git clone https://github.com/monadical-sas/reflector.git`
+3. Configure `.env` with HuggingFace token
+4. Start service (Docker compose or systemd)
+5. Set up Caddy reverse proxy for HTTPS
+
+**Save your API key and HTTPS URL** - you'll need them for Step 4.
+
 ---
 
 ## Step 3: Prepare Server
@@ -102,12 +137,9 @@ ssh user@your-server-ip
 docker --version  # verify
 ```
 
-### Open Firewall
+### Firewall
 
-```bash
-sudo ufw allow 80/tcp
-sudo ufw allow 443/tcp
-```
+Ensure ports 80 (HTTP) and 443 (HTTPS) are open for inbound traffic. The method varies by cloud provider and OS configuration.
 
 ### Clone Repository
 
@@ -120,7 +152,7 @@ cd reflector
 
 ## Step 4: Configure Environment
 
-**Location: YOUR SERVER (via SSH)**
+**Location: YOUR SERVER (via SSH, in the `reflector` directory)**
 
 Reflector has two env files:
 - `server/.env` - Backend configuration
@@ -129,7 +161,7 @@ Reflector has two env files:
 ### Backend Configuration
 
 ```bash
-cp server/env.example server/.env
+cp server/.env.example server/.env
 nano server/.env
 ```
 
@@ -151,15 +183,24 @@ CORS_ALLOW_CREDENTIALS=true
 # Secret key - generate with: openssl rand -hex 32
 SECRET_KEY=<your-generated-secret>
 
-# Modal GPU (paste from deploy-all.sh output)
+# GPU Processing - choose ONE option from Step 2:
+
+# Option A: Modal.com (paste from deploy-all.sh output)
 TRANSCRIPT_BACKEND=modal
 TRANSCRIPT_URL=https://yourname--reflector-transcriber-web.modal.run
 TRANSCRIPT_MODAL_API_KEY=<from-deploy-all.sh-output>
-
 DIARIZATION_BACKEND=modal
 DIARIZATION_URL=https://yourname--reflector-diarizer-web.modal.run
 DIARIZATION_MODAL_API_KEY=<from-deploy-all.sh-output>
 
+# Option B: Self-hosted GPU (use your GPU server URL and API key)
+# TRANSCRIPT_BACKEND=modal
+# TRANSCRIPT_URL=https://gpu.example.com
+# TRANSCRIPT_MODAL_API_KEY=<your-generated-api-key>
+# DIARIZATION_BACKEND=modal
+# DIARIZATION_URL=https://gpu.example.com
+# DIARIZATION_MODAL_API_KEY=<your-generated-api-key>
+
 # Storage - where to store audio files and transcripts
 TRANSCRIPT_STORAGE_BACKEND=local
 
@@ -205,7 +246,8 @@ cp Caddyfile.example Caddyfile
 nano Caddyfile
 ```
 
-Replace `example.com` with your domains:
+Replace `example.com` with your domains. The `{$VAR:default}` syntax uses Caddy's env var substitution - you can either edit the file directly or set `FRONTEND_DOMAIN` and `API_DOMAIN` environment variables.
+
 ```
 {$FRONTEND_DOMAIN:app.example.com} {
     reverse_proxy web:3000
@@ -226,9 +268,13 @@ Replace `example.com` with your domains:
 docker compose -f docker-compose.prod.yml up -d
 ```
 
-Wait for containers to start (~30 seconds), then run migrations:
+Wait for PostgreSQL to be ready, then run migrations:
 
 ```bash
+# Wait for postgres to be healthy (may take 30-60 seconds on first run)
+docker compose -f docker-compose.prod.yml exec postgres pg_isready -U reflector
+
+# Run database migrations
 docker compose -f docker-compose.prod.yml exec server uv run alembic upgrade head
 ```
 
@@ -332,6 +378,7 @@ docker compose -f docker-compose.prod.yml logs
 
 ## Next Steps
 
-- [Modal Setup](./modal-setup) - GPU processing details
+- [Modal Setup](./modal-setup) - Cloud GPU processing details
+- [Self-Hosted GPU Setup](./self-hosted-gpu-setup) - Own GPU server deployment
 - [Authentication Setup](./auth-setup) - Authentik OAuth
 - [System Requirements](./requirements) - Hardware specs
diff --git a/docs/docs/installation/self-hosted-gpu-setup.md b/docs/docs/installation/self-hosted-gpu-setup.md
new file mode 100644
index 00000000..288685e4
--- /dev/null
+++ b/docs/docs/installation/self-hosted-gpu-setup.md
@@ -0,0 +1,514 @@
+---
+sidebar_position: 5
+title: Self-Hosted GPU Setup
+---
+
+# Self-Hosted GPU Setup
+
+This guide covers deploying Reflector's GPU processing on your own server instead of Modal.com. For the complete deployment guide, see [Deployment Guide](./overview).
+
+## When to Use Self-Hosted GPU
+
+**Choose self-hosted GPU if you:**
+- Have GPU hardware available (NVIDIA required)
+- Want full control over processing
+- Prefer fixed infrastructure costs over pay-per-use
+- Have privacy or data locality requirements
+- Need to process audio without external API calls
+
+**Choose Modal.com instead if you:**
+- Don't have GPU hardware
+- Want zero infrastructure management
+- Prefer pay-per-use pricing
+- Need instant scaling for variable workloads
+
+See [Modal.com Setup](./modal-setup) for cloud GPU deployment.
+
+## What Gets Deployed
+
+The self-hosted GPU service provides the same API endpoints as Modal:
+- `POST /v1/audio/transcriptions` - Whisper transcription
+- `POST /diarize` - Pyannote speaker diarization
+
+Your main Reflector server connects to this service exactly like it connects to Modal - only the URL changes.
+
+## Prerequisites
+
+### Hardware
+- **GPU**: NVIDIA GPU with 8GB+ VRAM (tested on Tesla T4 with 15GB)
+- **CPU**: 4+ cores recommended
+- **RAM**: 8GB minimum, 16GB recommended
+- **Disk**:
+  - Docker method: 40-50GB minimum
+  - Systemd method: 25-30GB minimum
+
+### Software
+- Ubuntu 22.04 or 24.04
+- Public IP address
+- Domain name with DNS A record pointing to server
+
+### Accounts
+- **HuggingFace account** with accepted Pyannote licenses:
+  - https://huggingface.co/pyannote/speaker-diarization-3.1
+  - https://huggingface.co/pyannote/segmentation-3.0
+- **HuggingFace access token** from https://huggingface.co/settings/tokens
+
+## Choose Deployment Method
+
+### Docker Deployment (Recommended)
+
+**Pros:**
+- Container isolation and reproducibility
+- No manual library path configuration
+- Easier to replicate across servers
+- Built-in restart policies
+- Simpler dependency management
+
+**Cons:**
+- Higher disk usage (~15GB for container)
+- Requires 40-50GB disk minimum
+
+**Best for:** Teams wanting reproducible deployments, multiple GPU servers
+
+### Systemd Deployment
+
+**Pros:**
+- Lower disk usage (~8GB total)
+- Direct GPU access (no container layer)
+- Works on smaller disks (25-30GB)
+
+**Cons:**
+- Manual `LD_LIBRARY_PATH` configuration
+- Less portable across systems
+
+**Best for:** Single GPU server, limited disk space
+
+---
+
+## Docker Deployment
+
+### Step 1: Install NVIDIA Driver
+
+```bash
+sudo apt update
+sudo apt install -y nvidia-driver-535
+
+# Load kernel modules
+sudo modprobe nvidia
+
+# Verify installation
+nvidia-smi
+```
+
+Expected output: GPU details with driver version and CUDA version.
+
+### Step 2: Install Docker
+
+```bash
+curl -fsSL https://get.docker.com | sudo sh
+sudo usermod -aG docker $USER
+
+# Log out and back in for group changes
+exit
+# SSH back in
+```
+
+### Step 3: Install NVIDIA Container Toolkit
+
+```bash
+# Add NVIDIA repository
+curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | \
+  sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg
+
+curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
+  sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
+  sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
+
+# Install toolkit
+sudo apt-get update
+sudo apt-get install -y nvidia-container-toolkit
+
+# Configure Docker runtime
+sudo nvidia-ctk runtime configure --runtime=docker
+sudo systemctl restart docker
+```
+
+### Step 4: Clone Repository and Configure
+
+```bash
+git clone https://github.com/monadical-sas/reflector.git
+cd reflector/gpu/self_hosted
+
+# Create environment file
+cat > .env << EOF
+REFLECTOR_GPU_APIKEY=$(openssl rand -hex 16)
+HF_TOKEN=your_huggingface_token_here
+EOF
+
+# Note the generated API key - you'll need it for main server config
+cat .env
+```
+
+### Step 5: Create Docker Compose File
+
+```bash
+cat > compose.yml << 'EOF'
+services:
+  reflector_gpu:
+    build:
+      context: .
+    ports:
+      - "8000:8000"
+    env_file:
+      - .env
+    volumes:
+      - ./cache:/root/.cache
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [gpu]
+    restart: unless-stopped
+EOF
+```
+
+### Step 6: Build and Start
+
+```bash
+# Build image (takes ~5 minutes, downloads ~10GB)
+sudo docker compose build
+
+# Start service
+sudo docker compose up -d
+
+# Wait for startup and verify
+sleep 30
+sudo docker compose logs
+```
+
+Look for: `INFO: Application startup complete. Uvicorn running on http://0.0.0.0:8000`
+
+### Step 7: Verify GPU Access
+
+```bash
+# Check GPU is accessible from container
+sudo docker exec $(sudo docker ps -q) nvidia-smi
+```
+
+Should show GPU with ~3GB VRAM used (models loaded).
+
+---
+
+## Systemd Deployment
+
+### Step 1: Install NVIDIA Driver
+
+```bash
+sudo apt update
+sudo apt install -y nvidia-driver-535
+
+# Load kernel modules
+sudo modprobe nvidia
+
+# Verify installation
+nvidia-smi
+```
+
+### Step 2: Install Dependencies
+
+```bash
+# Install ffmpeg
+sudo apt install -y ffmpeg
+
+# Install uv package manager
+curl -LsSf https://astral.sh/uv/install.sh | sh
+source ~/.local/bin/env
+
+# Clone repository
+git clone https://github.com/monadical-sas/reflector.git
+cd reflector/gpu/self_hosted
+```
+
+### Step 3: Configure Environment
+
+```bash
+# Create environment file
+cat > .env << EOF
+REFLECTOR_GPU_APIKEY=$(openssl rand -hex 16)
+HF_TOKEN=your_huggingface_token_here
+EOF
+
+# Note the generated API key
+cat .env
+```
+
+### Step 4: Install Python Packages
+
+```bash
+# Install dependencies (~3GB download)
+uv sync
+```
+
+### Step 5: Create Systemd Service
+
+```bash
+# Generate library paths for NVIDIA packages
+export NVIDIA_LIBS=$(find ~/reflector/gpu/self_hosted/.venv/lib/python3.12/site-packages/nvidia -name lib -type d | tr '\n' ':')
+
+# Load environment variables
+source ~/reflector/gpu/self_hosted/.env
+
+# Create service file
+sudo tee /etc/systemd/system/reflector-gpu.service << EOFSVC
+[Unit]
+Description=Reflector GPU Service (Transcription & Diarization)
+After=network.target
+
+[Service]
+Type=simple
+User=$USER
+WorkingDirectory=$HOME/reflector/gpu/self_hosted
+Environment="PATH=$HOME/.local/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
+Environment="HF_TOKEN=${HF_TOKEN}"
+Environment="REFLECTOR_GPU_APIKEY=${REFLECTOR_GPU_APIKEY}"
+Environment="LD_LIBRARY_PATH=${NVIDIA_LIBS}"
+ExecStart=$HOME/reflector/gpu/self_hosted/.venv/bin/uvicorn main:app --host 0.0.0.0 --port 8000
+Restart=always
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target
+EOFSVC
+
+# Enable and start
+sudo systemctl daemon-reload
+sudo systemctl enable reflector-gpu
+sudo systemctl start reflector-gpu
+```
+
+### Step 6: Verify Service
+
+```bash
+# Check status
+sudo systemctl status reflector-gpu
+
+# View logs
+sudo journalctl -u reflector-gpu -f
+```
+
+Look for: `INFO: Application startup complete.`
+
+---
+
+## Configure HTTPS with Caddy
+
+Both deployment methods need HTTPS for production. Caddy handles SSL automatically.
+
+### Install Caddy
+
+```bash
+sudo apt install -y debian-keyring debian-archive-keyring apt-transport-https curl
+
+curl -1sLf 'https://dl.cloudsmith.io/public/caddy/stable/gpg.key' | \
+  sudo gpg --dearmor -o /usr/share/keyrings/caddy-stable-archive-keyring.gpg
+
+curl -1sLf 'https://dl.cloudsmith.io/public/caddy/stable/debian.deb.txt' | \
+  sudo tee /etc/apt/sources.list.d/caddy-stable.list
+
+sudo apt update
+sudo apt install -y caddy
+```
+
+### Configure Reverse Proxy
+
+```bash
+sudo tee /etc/caddy/Caddyfile << 'EOF'
+gpu.example.com {
+    reverse_proxy localhost:8000
+}
+EOF
+
+# Reload Caddy (auto-provisions SSL certificate)
+sudo systemctl reload caddy
+```
+
+Replace `gpu.example.com` with your domain.
+
+### Verify HTTPS
+
+```bash
+curl -I https://gpu.example.com/docs
+# Should return HTTP/2 200
+```
+
+---
+
+## Configure Main Reflector Server
+
+On your main Reflector server, update `server/.env`:
+
+```env
+# GPU Processing - Self-hosted
+TRANSCRIPT_BACKEND=modal
+TRANSCRIPT_URL=https://gpu.example.com
+TRANSCRIPT_MODAL_API_KEY=<your-generated-api-key>
+
+DIARIZATION_BACKEND=modal
+DIARIZATION_URL=https://gpu.example.com
+DIARIZATION_MODAL_API_KEY=<your-generated-api-key>
+```
+
+**Note:** The backend type is `modal` because the self-hosted GPU service implements the same API contract as Modal.com. This allows you to switch between cloud and self-hosted GPU processing by only changing the URL and API key.
+
+Restart services to apply:
+
+```bash
+docker compose -f docker-compose.prod.yml restart server worker
+```
+
+---
+
+## Service Management
+
+All commands in this section assume you're in `~/reflector/gpu/self_hosted/`.
+
+### Docker
+
+```bash
+# View logs
+sudo docker compose logs -f
+
+# Restart service
+sudo docker compose restart
+
+# Stop service
+sudo docker compose down
+
+# Check status
+sudo docker compose ps
+```
+
+### Systemd
+
+```bash
+# View logs
+sudo journalctl -u reflector-gpu -f
+
+# Restart service
+sudo systemctl restart reflector-gpu
+
+# Stop service
+sudo systemctl stop reflector-gpu
+
+# Check status
+sudo systemctl status reflector-gpu
+```
+
+### Monitor GPU
+
+```bash
+# Check GPU usage
+nvidia-smi
+
+# Watch in real-time
+watch -n 1 nvidia-smi
+```
+
+**Typical GPU memory usage:**
+- Idle (models loaded): ~3GB VRAM
+- During transcription: ~4-5GB VRAM
+
+---
+
+## Performance Notes
+
+**Tesla T4 benchmarks:**
+- Transcription: ~2-3x real-time (10 min audio in 3-5 min)
+- Diarization: ~1.5x real-time
+- Max concurrent requests: 2-3 (depends on audio length)
+- First request warmup: ~10 seconds (model loading)
+
+---
+
+## Troubleshooting
+
+### nvidia-smi fails after driver install
+
+```bash
+# Manually load kernel modules
+sudo modprobe nvidia
+nvidia-smi
+```
+
+### Service fails with "Could not download pyannote pipeline"
+
+1. Verify HF_TOKEN is valid: `echo $HF_TOKEN`
+2. Check model access at https://huggingface.co/pyannote/speaker-diarization-3.1
+3. Regenerate service/compose with correct token
+4. Restart service
+
+### cuDNN library loading errors (Systemd only)
+
+Symptom: `Unable to load libcudnn_cnn.so`
+
+Regenerate the systemd service file - the `LD_LIBRARY_PATH` must include all NVIDIA package directories.
+
+### Cannot connect to HTTPS endpoint
+
+1. Verify DNS resolves: `dig +short gpu.example.com`
+2. Check firewall: `sudo ufw status` (ports 80, 443 must be open)
+3. Check Caddy: `sudo systemctl status caddy`
+4. View Caddy logs: `sudo journalctl -u caddy -n 50`
+
+### SSL certificate not provisioning
+
+Requirements for Let's Encrypt:
+- Ports 80 and 443 publicly accessible
+- DNS resolves to server's public IP
+- Valid domain (not localhost or private IP)
+
+### Docker container won't start
+
+```bash
+# Check logs
+sudo docker compose logs
+
+# Common issues:
+# - Port 8000 already in use
+# - GPU not accessible (nvidia-ctk not configured)
+# - Missing .env file
+```
+
+---
+
+## Security Considerations
+
+1. **API Key**: Keep `REFLECTOR_GPU_APIKEY` secret, rotate periodically
+2. **HuggingFace Token**: Treat as password, never commit to git
+3. **Firewall**: Only expose ports 80 and 443 publicly
+4. **Updates**: Regularly update system packages
+5. **Monitoring**: Set up alerts for service failures
+
+---
+
+## Updating
+
+### Docker
+
+```bash
+cd ~/reflector/gpu/self_hosted
+git pull
+sudo docker compose build
+sudo docker compose up -d
+```
+
+### Systemd
+
+```bash
+cd ~/reflector/gpu/self_hosted
+git pull
+uv sync
+sudo systemctl restart reflector-gpu
+```
diff --git a/gpu/modal_deployments/reflector_diarizer.py b/gpu/modal_deployments/reflector_diarizer.py
index 9bcc8a4e..816e17cf 100644
--- a/gpu/modal_deployments/reflector_diarizer.py
+++ b/gpu/modal_deployments/reflector_diarizer.py
@@ -24,6 +24,12 @@ app = modal.App(name="reflector-diarizer")
 upload_volume = modal.Volume.from_name("diarizer-uploads", create_if_missing=True)
 
 
+# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
+# If you modify the audio format detection logic, you MUST update all copies:
+#   - gpu/self_hosted/app/utils.py
+#   - gpu/modal_deployments/reflector_transcriber.py (2 copies)
+#   - gpu/modal_deployments/reflector_transcriber_parakeet.py
+#   - gpu/modal_deployments/reflector_diarizer.py (this file)
 def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtension:
     parsed_url = urlparse(url)
     url_path = parsed_url.path
@@ -39,6 +45,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtens
         return AudioFileExtension("wav")
     if "audio/mp4" in content_type:
         return AudioFileExtension("mp4")
+    if "audio/webm" in content_type or "video/webm" in content_type:
+        return AudioFileExtension("webm")
 
     raise ValueError(
         f"Unsupported audio format for URL: {url}. "
diff --git a/gpu/modal_deployments/reflector_transcriber.py b/gpu/modal_deployments/reflector_transcriber.py
index 3f652de9..fbd41083 100644
--- a/gpu/modal_deployments/reflector_transcriber.py
+++ b/gpu/modal_deployments/reflector_transcriber.py
@@ -99,6 +99,12 @@ image = (
 )
 
 
+# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
+# If you modify the audio format detection logic, you MUST update all copies:
+#   - gpu/self_hosted/app/utils.py
+#   - gpu/modal_deployments/reflector_transcriber.py (this file - 2 copies!)
+#   - gpu/modal_deployments/reflector_transcriber_parakeet.py
+#   - gpu/modal_deployments/reflector_diarizer.py
 def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtension:
     parsed_url = urlparse(url)
     url_path = parsed_url.path
@@ -114,6 +120,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtens
         return AudioFileExtension("wav")
     if "audio/mp4" in content_type:
         return AudioFileExtension("mp4")
+    if "audio/webm" in content_type or "video/webm" in content_type:
+        return AudioFileExtension("webm")
 
     raise ValueError(
         f"Unsupported audio format for URL: {url}. "
@@ -316,6 +324,11 @@ class TranscriberWhisperFile:
         import numpy as np
         from silero_vad import VADIterator
 
+        # IMPORTANT: This VAD segment logic is duplicated in multiple files for deployment isolation.
+        # If you modify this function, you MUST update all copies:
+        #   - gpu/modal_deployments/reflector_transcriber.py (this file)
+        #   - gpu/modal_deployments/reflector_transcriber_parakeet.py
+        #   - gpu/self_hosted/app/services/transcriber.py
         def vad_segments(
             audio_array,
             sample_rate: int = SAMPLERATE,
@@ -323,6 +336,7 @@ class TranscriberWhisperFile:
         ) -> Generator[TimeSegment, None, None]:
             """Generate speech segments as TimeSegment using Silero VAD."""
             iterator = VADIterator(self.vad_model, sampling_rate=sample_rate)
+            audio_duration = len(audio_array) / float(SAMPLERATE)
             start = None
             for i in range(0, len(audio_array), window_size):
                 chunk = audio_array[i : i + window_size]
@@ -342,6 +356,9 @@ class TranscriberWhisperFile:
                         start / float(SAMPLERATE), end / float(SAMPLERATE)
                     )
                     start = None
+            # Handle case where audio ends while speech is still active
+            if start is not None:
+                yield TimeSegment(start / float(SAMPLERATE), audio_duration)
             iterator.reset_states()
 
         upload_volume.reload()
@@ -407,6 +424,12 @@ class TranscriberWhisperFile:
         return {"text": " ".join(all_text), "words": all_words}
 
 
+# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
+# If you modify the audio format detection logic, you MUST update all copies:
+#   - gpu/self_hosted/app/utils.py
+#   - gpu/modal_deployments/reflector_transcriber.py (this file - 2 copies!)
+#   - gpu/modal_deployments/reflector_transcriber_parakeet.py
+#   - gpu/modal_deployments/reflector_diarizer.py
 def detect_audio_format(url: str, headers: dict) -> str:
     from urllib.parse import urlparse
 
@@ -424,6 +447,8 @@ def detect_audio_format(url: str, headers: dict) -> str:
         return "wav"
     if "audio/mp4" in content_type:
         return "mp4"
+    if "audio/webm" in content_type or "video/webm" in content_type:
+        return "webm"
 
     raise HTTPException(
         status_code=400,
diff --git a/gpu/modal_deployments/reflector_transcriber_parakeet.py b/gpu/modal_deployments/reflector_transcriber_parakeet.py
index 5f326b77..046f1a7c 100644
--- a/gpu/modal_deployments/reflector_transcriber_parakeet.py
+++ b/gpu/modal_deployments/reflector_transcriber_parakeet.py
@@ -90,6 +90,12 @@ image = (
 )
 
 
+# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
+# If you modify the audio format detection logic, you MUST update all copies:
+#   - gpu/self_hosted/app/utils.py
+#   - gpu/modal_deployments/reflector_transcriber.py (2 copies)
+#   - gpu/modal_deployments/reflector_transcriber_parakeet.py (this file)
+#   - gpu/modal_deployments/reflector_diarizer.py
 def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtension:
     parsed_url = urlparse(url)
     url_path = parsed_url.path
@@ -105,6 +111,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> AudioFileExtens
         return AudioFileExtension("wav")
     if "audio/mp4" in content_type:
         return AudioFileExtension("mp4")
+    if "audio/webm" in content_type or "video/webm" in content_type:
+        return AudioFileExtension("webm")
 
     raise ValueError(
         f"Unsupported audio format for URL: {url}. "
@@ -301,6 +309,11 @@ class TranscriberParakeetFile:
             audio_array, sample_rate = librosa.load(file_path, sr=SAMPLERATE, mono=True)
             return audio_array
 
+        # IMPORTANT: This VAD segment logic is duplicated in multiple files for deployment isolation.
+        # If you modify this function, you MUST update all copies:
+        #   - gpu/modal_deployments/reflector_transcriber.py
+        #   - gpu/modal_deployments/reflector_transcriber_parakeet.py (this file)
+        #   - gpu/self_hosted/app/services/transcriber.py
         def vad_segment_generator(
             audio_array,
         ) -> Generator[TimeSegment, None, None]:
diff --git a/gpu/self_hosted/DEV_SETUP.md b/gpu/self_hosted/DEV_SETUP.md
new file mode 100644
index 00000000..9b76865c
--- /dev/null
+++ b/gpu/self_hosted/DEV_SETUP.md
@@ -0,0 +1,137 @@
+# Local Development GPU Setup
+
+Run transcription and diarization locally for development/testing.
+
+> **For production deployment**, see the [Self-Hosted GPU Setup Guide](../../docs/docs/installation/self-hosted-gpu-setup.md).
+
+## Prerequisites
+
+1. **Python 3.12+** and **uv** package manager
+2. **FFmpeg** installed and on PATH
+3. **HuggingFace account** with access to pyannote models
+
+### Accept Pyannote Licenses (Required)
+
+Before first run, accept licenses for these gated models (logged into HuggingFace):
+- https://hf.co/pyannote/speaker-diarization-3.1
+- https://hf.co/pyannote/segmentation-3.0
+
+## Quick Start
+
+### 1. Install dependencies
+
+```bash
+cd gpu/self_hosted
+uv sync
+```
+
+### 2. Start the GPU service
+
+```bash
+cd gpu/self_hosted
+HF_TOKEN=<your-huggingface-token> \
+REFLECTOR_GPU_APIKEY=dev-key-12345 \
+.venv/bin/uvicorn main:app --host 0.0.0.0 --port 8000
+```
+
+Note: The `.env` file is NOT auto-loaded. Pass env vars explicitly or use:
+```bash
+export HF_TOKEN=<your-token>
+export REFLECTOR_GPU_APIKEY=dev-key-12345
+.venv/bin/uvicorn main:app --host 0.0.0.0 --port 8000
+```
+
+### 3. Configure Reflector to use local GPU
+
+Edit `server/.env`:
+
+```bash
+# Transcription - local GPU service
+TRANSCRIPT_BACKEND=modal
+TRANSCRIPT_URL=http://host.docker.internal:8000
+TRANSCRIPT_MODAL_API_KEY=dev-key-12345
+
+# Diarization - local GPU service
+DIARIZATION_BACKEND=modal
+DIARIZATION_URL=http://host.docker.internal:8000
+DIARIZATION_MODAL_API_KEY=dev-key-12345
+```
+
+Note: Use `host.docker.internal` because Reflector server runs in Docker.
+
+### 4. Restart Reflector server
+
+```bash
+cd server
+docker compose restart server worker
+```
+
+## Testing
+
+### Test transcription
+
+```bash
+curl -s -X POST http://localhost:8000/v1/audio/transcriptions \
+  -H "Authorization: Bearer dev-key-12345" \
+  -F "file=@/path/to/audio.wav" \
+  -F "language=en"
+```
+
+### Test diarization
+
+```bash
+curl -s -X POST "http://localhost:8000/diarize?audio_file_url=<audio-url>" \
+  -H "Authorization: Bearer dev-key-12345"
+```
+
+## Platform Notes
+
+### macOS (ARM)
+
+Docker build fails - CUDA packages are x86_64 only. Use local Python instead:
+```bash
+uv sync
+HF_TOKEN=xxx REFLECTOR_GPU_APIKEY=xxx .venv/bin/uvicorn main:app --host 0.0.0.0 --port 8000
+```
+
+### Linux with NVIDIA GPU
+
+Docker works with CUDA acceleration:
+```bash
+docker compose up -d
+```
+
+### CPU-only
+
+Works on any platform, just slower. PyTorch auto-detects and falls back to CPU.
+
+## Switching Back to Modal.com
+
+Edit `server/.env`:
+
+```bash
+TRANSCRIPT_BACKEND=modal
+TRANSCRIPT_URL=https://monadical-sas--reflector-transcriber-parakeet-web.modal.run
+TRANSCRIPT_MODAL_API_KEY=<modal-api-key>
+
+DIARIZATION_BACKEND=modal
+DIARIZATION_URL=https://monadical-sas--reflector-diarizer-web.modal.run
+DIARIZATION_MODAL_API_KEY=<modal-api-key>
+```
+
+## Troubleshooting
+
+### "Could not download pyannote pipeline"
+- Accept model licenses at HuggingFace (see Prerequisites)
+- Verify HF_TOKEN is set and valid
+
+### Service won't start
+- Check port 8000 is free: `lsof -i :8000`
+- Kill orphan processes if needed
+
+### Transcription returns empty text
+- Ensure audio contains speech (not just tones/silence)
+- Check audio format is supported (wav, mp3, etc.)
+
+### Deprecation warnings from torchaudio/pyannote
+- Safe to ignore - doesn't affect functionality
diff --git a/gpu/self_hosted/README.md b/gpu/self_hosted/README.md
index 0180a8ae..395e05a6 100644
--- a/gpu/self_hosted/README.md
+++ b/gpu/self_hosted/README.md
@@ -56,9 +56,13 @@ Docker
 
 - Not yet provided in this directory. A Dockerfile will be added later. For now, use Local run above
 
-Conformance tests
+# Setup
 
-# From this directory
+[SETUP.md](SETUP.md)
+
+# Conformance tests
+
+## From this directory
 
 TRANSCRIPT_URL=http://localhost:8000 \
 TRANSCRIPT_API_KEY=dev-key \
diff --git a/gpu/self_hosted/app/services/transcriber.py b/gpu/self_hosted/app/services/transcriber.py
index 26a313cc..21e55fe5 100644
--- a/gpu/self_hosted/app/services/transcriber.py
+++ b/gpu/self_hosted/app/services/transcriber.py
@@ -129,6 +129,11 @@ class WhisperService:
             audio = np.frombuffer(proc.stdout, dtype=np.float32)
             return audio
 
+        # IMPORTANT: This VAD segment logic is duplicated in multiple files for deployment isolation.
+        # If you modify this function, you MUST update all copies:
+        #   - gpu/modal_deployments/reflector_transcriber.py
+        #   - gpu/modal_deployments/reflector_transcriber_parakeet.py
+        #   - gpu/self_hosted/app/services/transcriber.py (this file)
         def vad_segments(
             audio_array,
             sample_rate: int = SAMPLE_RATE,
@@ -153,6 +158,10 @@ class WhisperService:
                     end = speech["end"]
                     yield (start / float(SAMPLE_RATE), end / float(SAMPLE_RATE))
                     start = None
+            # Handle case where audio ends while speech is still active
+            if start is not None:
+                audio_duration = len(audio_array) / float(sample_rate)
+                yield (start / float(SAMPLE_RATE), audio_duration)
             iterator.reset_states()
 
         audio_array = load_audio_via_ffmpeg(file_path, SAMPLE_RATE)
diff --git a/gpu/self_hosted/app/utils.py b/gpu/self_hosted/app/utils.py
index 679804cb..7200cfa2 100644
--- a/gpu/self_hosted/app/utils.py
+++ b/gpu/self_hosted/app/utils.py
@@ -34,6 +34,12 @@ def ensure_dirs():
     UPLOADS_PATH.mkdir(parents=True, exist_ok=True)
 
 
+# IMPORTANT: This function is duplicated in multiple files for deployment isolation.
+# If you modify the audio format detection logic, you MUST update all copies:
+#   - gpu/self_hosted/app/utils.py (this file)
+#   - gpu/modal_deployments/reflector_transcriber.py (2 copies)
+#   - gpu/modal_deployments/reflector_transcriber_parakeet.py
+#   - gpu/modal_deployments/reflector_diarizer.py
 def detect_audio_format(url: str, headers: Mapping[str, str]) -> str:
     url_path = urlparse(url).path
     for ext in SUPPORTED_FILE_EXTENSIONS:
@@ -47,6 +53,8 @@ def detect_audio_format(url: str, headers: Mapping[str, str]) -> str:
         return "wav"
     if "audio/mp4" in content_type:
         return "mp4"
+    if "audio/webm" in content_type or "video/webm" in content_type:
+        return "webm"
 
     raise HTTPException(
         status_code=400,
diff --git a/server/env.example b/server/.env.example
similarity index 100%
rename from server/env.example
rename to server/.env.example
diff --git a/server/reflector/settings.py b/server/reflector/settings.py
index 1ec46d94..3f78f393 100644
--- a/server/reflector/settings.py
+++ b/server/reflector/settings.py
@@ -30,7 +30,9 @@ class Settings(BaseSettings):
     AUDIO_CHUNKER_BACKEND: str = "frames"
 
     # Audio Transcription
-    # backends: whisper, modal
+    # backends:
+    #   - whisper: in-process model loading (no HTTP, runs in same process)
+    #   - modal: HTTP API client (works with Modal.com OR self-hosted gpu/self_hosted/)
     TRANSCRIPT_BACKEND: str = "whisper"
     TRANSCRIPT_URL: str | None = None
     TRANSCRIPT_TIMEOUT: int = 90
@@ -75,6 +77,9 @@ class Settings(BaseSettings):
     LLM_CONTEXT_WINDOW: int = 16000
 
     # Diarization
+    # backends:
+    #   - pyannote: in-process model loading (no HTTP, runs in same process)
+    #   - modal: HTTP API client (works with Modal.com OR self-hosted gpu/self_hosted/)
     DIARIZATION_ENABLED: bool = True
     DIARIZATION_BACKEND: str = "modal"
     DIARIZATION_URL: str | None = None