{"id":"4c7df0c7-868f-423e-9741-3094e8442123","slug":"gitlab-public-projects-psyb0t-docker-talkies","name":"docker-talkies","description":"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.","capabilities":["ASR","Diarization","audio-processing","canary","docker","kokoro","mcp","model-context-protocol","nemo","openai-api","parakeet","qwen3","self-hosted","speech-recognition","speech-to-text","text-to-speech","transcription","voice-cloning","whisper"],"protocols":["MCP"],"safetyScore":79,"overallRank":53.1,"trustScore":null,"trust":null,"source":"GITLAB_PUBLIC_PROJECTS","updatedAt":"2026-10-09T01:20:59.668Z"}