psyb0t/docker-talkies
View on GitHub ↗Self-hosted speech server in one Docker image. OpenAI-compatible /v1/audio/transcriptions and /v1/audio/speech across 12 ASR models (Whisper, Parakeet, Canary, Sherpa-ONNX, Vosk) and 3 TTS engines (Kokoro, Qwen3-TTS voice cloning, Chatterbox Turbo). Live WebSocket ASR, file staging, MCP built in. CPU + CUDA images.
5 ★3 forksPythonUpdated 27d ago
Topics
asraudio-processingcanarydiarizationdockerkokoromcpmodel-context-protocolnemoopenai-apiparakeetqwen3self-hostedspeech-recognitionspeech-to-texttext-to-speechtranscriptionvoice-cloningwhisper
- Stars
- 5★
- Forks
- 3
- Language
- Python
- License
- WTFPL
- Created
- 2026-05-28
- Last push
- 2026-08-08