io.github.modelscope

funasr-mcp

FunASR

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

stdioofficialapplication

Package Details

ghcr.io/modelscope/funasr-mcp:0.1.1

https://github.com/modelscope/funasr-mcp/pkgs/container/funasr-mcp
Transportstdio
Runtimedocker

Runtime Arguments

Named
--mount
type=bind,src={audio_directory},dst=/audio,readonlyMount the host audio directory read-only at /audio in the container.
--mount
type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscopePersist downloaded ModelScope model files between container runs.