GitBucket
|
Initial voice TTS server with F5-TTS backend, WebSocket streaming and warm-up
- FastAPI WebSocket API for real-time chunked TTS - F5-TTS GPU backend with reference caching and auto-transcription - Dummy backend for offline tests - Streaming text segmenter, session state, stop/resume - Startup warm-up, PCM16/base64 audio, basic tests - Documentation: architecture, protocol, usage, roadmap, technical notes |
|---|
|
|
| .env.example 0 → 100644 |
|---|
| .gitignore 0 → 100644 |
|---|
| README.md |
|---|
| docs/01_overview.md 0 → 100644 |
|---|
| docs/02_architecture.md 0 → 100644 |
|---|
| docs/03_websocket_protocol.md 0 → 100644 |
|---|
| docs/04_roadmap.md 0 → 100644 |
|---|
| docs/05_usage.md 0 → 100644 |
|---|
| docs/06_technical_notes.md 0 → 100644 |
|---|
| pyproject.toml 0 → 100644 |
|---|
| requirements.txt 0 → 100644 |
|---|
| scripts/download_f5_tts.py 0 → 100644 |
|---|
| src/voice_tts/api/protocol.py 0 → 100644 |
|---|
| src/voice_tts/api/server.py 0 → 100644 |
|---|
| src/voice_tts/audio/formats.py 0 → 100644 |
|---|
| src/voice_tts/config.py 0 → 100644 |
|---|
| src/voice_tts/main.py 0 → 100644 |
|---|
| src/voice_tts/session/state.py 0 → 100644 |
|---|
| src/voice_tts/tts/engine.py 0 → 100644 |
|---|
| src/voice_tts/tts/f5_backend.py 0 → 100644 |
|---|
| src/voice_tts/tts/segmenter.py 0 → 100644 |
|---|
| src/voice_tts/tts/utils.py 0 → 100644 |
|---|
| tests/test_segmenter.py 0 → 100644 |
|---|
| tests/test_server.py 0 → 100644 |
|---|
| voices/.gitkeep 0 → 100644 |
|---|