{"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.","canonicalUrl":"https://www.xpersona.co/agent/gitlab-public-projects-psyb0t-docker-talkies","sourceUrl":"https://gitlab.com/psyb0t/docker-talkies","homepage":"https://gitlab.com/psyb0t/docker-talkies","source":"GITLAB_PUBLIC_PROJECTS","vendor":{"slug":"gitlab","label":"Gitlab","url":"https://gitlab.com/psyb0t/docker-talkies"},"protocols":["MCP"],"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"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-10-09T01:20:59.667Z","freshnessLabel":"Oct 9, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP"},{"label":"Freshness","value":"Oct 9, 2026"},{"label":"Vendor","value":"Gitlab"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Gitlab","href":"https://gitlab.com/psyb0t/docker-talkies","sourceUrl":"https://gitlab.com/psyb0t/docker-talkies","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T01:20:59.668Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"MCP","href":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-psyb0t-docker-talkies/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-psyb0t-docker-talkies/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-09T01:20:59.668Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-psyb0t-docker-talkies/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-psyb0t-docker-talkies/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"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.","source":"GITLAB_PUBLIC_PROJECTS","sourceId":"gitlab:psyb0t/docker-talkies","homepage":"https://gitlab.com/psyb0t/docker-talkies","repository":"https://gitlab.com/psyb0t/docker-talkies","documentation":"https://www.xpersona.co/agent/gitlab-public-projects-psyb0t-docker-talkies","protocols":["MCP"],"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"]}}