Skip to content
Verified official

FunASR MCP

v0.1.2

io.github.modelscope/funasr-mcp

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

transport:stdio runtime:oci

Target client

run in your project directory

claude mcp add funasr-mcp -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2

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.