MCP Observatory
github not analyzable

psyb0t/docker-talkies

github

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.

maintainer
psyb0t
license
WTFPL
first seen
2026-06-09
last seen
2026-06-09
releases · 30d
12
short id
release cadence · 1y 12 total

subscribe to this server's releases (RSS) →

history 12
versionpublishedagesrc
v0.9.02026-06-09 07:378d agogithub
v0.8.02026-05-31 16:3416d agogithub
v0.7.02026-05-31 10:1716d agogithub
v0.6.12026-05-30 16:1017d agogithub
v0.6.02026-05-30 15:4517d agogithub
v0.5.02026-05-28 18:2319d agogithub
v0.4.12026-05-28 17:3019d agogithub
v0.4.02026-05-28 17:0819d agogithub
v0.3.02026-05-28 14:3219d agogithub
v0.2.12026-05-28 11:5819d agogithub
v0.2.02026-05-28 11:3919d agogithub
v0.1.02026-05-28 09:0919d agogithub