D

docker-talkies

Project information

[mirror] OpenAI-compatible audio server in Docker. 7 ASR backends (Whisper, Distil-Whisper, Parakeet, Canary, Canary-Qwen) + 2 TTS engines (Kokoro, Qwen3-TTS voice cloning). Single /v1/audio/{transcriptions,speech,voices} surface. CPU + CUDA images. Hot model swap. MCP server built in.

ASR audio-proces... canary Diarization Docker kokoro mcp model-contex... nemo openai-api parakeet qwen3 self-hosted speech-recog... speech-to-text transcription whisper

49 Commits
2 Branches
31 Tags

README
Do What The F*ck You Want To Public License
CHANGELOG

Created on

July 31, 2026

Loading