Skip to content
mcp/harbor
Verified official

ffvoice MCP

v0.8.3

io.github.chicogong/ffvoice

Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud

transport:stdio runtime:pypi
View source

Target client

run in your project directory 

claude mcp add ffvoice -- uvx ffvoice

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.