Talkies — Claude Code MCP server for speech and transcription
A self-hosted speech server in one Docker image. Useful when an agent has to transcribe audio or speak text back.
Open on GitHubWhat Talkies does
Talkies runs as a local container. It covers file transcription, live ASR over WebSocket, speech synthesis in several formats, server-side file staging and model lifecycle controls. Agents reach the same features through the /v1/mcp endpoint, which exposes ASR and file tools. The transcription and speech routes mirror the OpenAI wire shapes where the contracts overlap; streaming, files, lifecycle and MCP are Talkies extensions.
On the first boot, pass TALKIES_ENABLED_MODELS to pull only the models you need. Skip it and the entrypoint downloads the whole bundled registry. Some models are CUDA-only: Parakeet-TDT, the larger Canary entries, Qwen3 TTS and Chatterbox Turbo need the psyb0t/talkies:latest-cuda image plus --gpus all. Keep the port on loopback as in the example, 127.0.0.1:8000 — GET /healthz is the one route that skips authentication.
Voice cloning is folder-based. Drop a .wav into /data/custom-voices and it shows up in GET /v1/audio/voices. Qwen3 can pair it with a sibling .txt transcript; Chatterbox takes the clip alone, and it has to run past five seconds. Chatterbox Turbo understands 19 inline tags such as [sigh] or [whispering], written lowercase in square brackets inside the input text. Any other bracketed word gets read out as literal text. Its audio carries a neural watermark unless you set TALKIES_CHATTERBOX_WATERMARK to false.
What it helps with
- turn a meeting recording into text with timestamps
- get IPA phones for what was actually spoken
- render a line as mp3 with a chosen voice
- stage an audio file on the server and fetch it by name
- evict a model from memory once you are done
Example prompts for the agent
- Transcribe
clip.wavwithwhisper-large-v3-turboand give me the text - Synthesize this line with
chatterbox-turboas mp3 - Copy
intro.wavinto/data/custom-voicesand list the voices
How to install Talkies
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Talkies
How do I install Talkies in Claude Code?
There is no install command. You start the server in Docker: `docker run --rm -it --name talkies -p 127.0.0.1:8000:8000 -v "$PWD/talkies-data:/data" -e TALKIES_ENABLED_MODELS=whisper-large-v3-turbo,kokoro-82m psyb0t/talkies:latest, then point the client at the /v1/mcp` endpoint.
What does Talkies do?
It serves transcription, live ASR over WebSocket, speech synthesis and file staging. Agents get the same tools through the MCP endpoint.
Which models need CUDA?
Parakeet-TDT, the larger Canary entries, Qwen3 TTS and Chatterbox Turbo. They require the psyb0t/talkies:latest-cuda image and a run with --gpus all.
