# FunASR > Transcribes audio files on your own machine with FunASR and SenseVoice, in Mandarin, Cantonese, English, Japanese and Korean. The FunASR MCP server is ModelScope's local speech-to-text server for agents. It runs FunASR, the open-source speech recognition toolkit, with the SenseVoiceSmall model on your own machine, so your agent can turn a recording into text without sending the audio to a cloud service and without an API key. What you can do with it - Transcribe a meeting recording, an interview or a voice memo from a file path - Recognise Mandarin, Cantonese, English, Japanese and Korean, detected automatically or set with a language hint - Get time-stamped segments along with the text when the model returns them - Split longer recordings with voice activity detection before recognition How it connects - A local server over stdio, published as the Docker image ghcr.io/modelscope/funasr-mcp - You mount one folder of audio files read-only at /audio, then ask about files by their /audio path, such as /audio/meeting.wav - A Docker volume keeps the downloaded model between runs - Without Docker, install funasr with pip and point your agent at funasr_mcp.py from the FunASR repository; FUNASR_DEVICE picks CPU, CUDA or Apple's MPS, and FUNASR_MODEL another model Good to know - One tool, transcribe_audio, which reads files and changes nothing - The first transcription downloads the model weights from ModelScope, so it takes longer than later ones - It takes WAV, MP3, FLAC and other common audio files; not URLs or live microphone audio - The Docker image runs on the CPU and is built for x86-64 machines - MIT licensed, maintained in the modelscope/FunASR repository - Type: Plugin - Made by: modelscope - Category: Media - Formats: Local MCP - Version: 0.1.2 - Website: https://github.com/modelscope/FunASR/tree/main/examples/mcp_server - Source: https://github.com/modelscope/funasr/tree/HEAD/examples/mcp_server - Page: https://pluginboard.ai/plugins/funasr ## Works with - Claude - GitHub Copilot - Cursor - Claude Code - Codex - Antigravity - Gemini CLI - OpenClaw - OpenCode - Hermes Agent ## Install ### Claude Add to claude_desktop_config.json: ```json { "mcpServers": { "funasr": { "command": "docker", "args": [ "run", "-i", "--rm", "--mount", "type=bind,src={audio_directory},dst=/audio,readonly", "--mount", "type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope", "ghcr.io/modelscope/funasr-mcp:0.1.2" ] } } } ``` ### GitHub Copilot Add to VS Code: vscode:mcp/install?%7B%22name%22%3A%22funasr%22%2C%22command%22%3A%22docker%22%2C%22args%22%3A%5B%22run%22%2C%22-i%22%2C%22--rm%22%2C%22--mount%22%2C%22type%3Dbind%2Csrc%3D%7Baudio_directory%7D%2Cdst%3D%2Faudio%2Creadonly%22%2C%22--mount%22%2C%22type%3Dvolume%2Csrc%3Dfunasr-mcp-cache%2Cdst%3D%2Froot%2F.cache%2Fmodelscope%22%2C%22ghcr.io%2Fmodelscope%2Ffunasr-mcp%3A0.1.2%22%5D%7D Run in your terminal: ```shell code --add-mcp '{"name":"funasr","command":"docker","args":["run","-i","--rm","--mount","type=bind,src={audio_directory},dst=/audio,readonly","--mount","type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope","ghcr.io/modelscope/funasr-mcp:0.1.2"]}' ``` Copilot CLI: ```shell copilot mcp add funasr -- docker run -i --rm --mount 'type=bind,src={audio_directory},dst=/audio,readonly' --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope ghcr.io/modelscope/funasr-mcp:0.1.2 ``` ### Cursor Add to Cursor: cursor://anysphere.cursor-deeplink/mcp/install?name=funasr&config=eyJjb21tYW5kIjoiZG9ja2VyIiwiYXJncyI6WyJydW4iLCItaSIsIi0tcm0iLCItLW1vdW50IiwidHlwZT1iaW5kLHNyYz17YXVkaW9fZGlyZWN0b3J5fSxkc3Q9L2F1ZGlvLHJlYWRvbmx5IiwiLS1tb3VudCIsInR5cGU9dm9sdW1lLHNyYz1mdW5hc3ItbWNwLWNhY2hlLGRzdD0vcm9vdC8uY2FjaGUvbW9kZWxzY29wZSIsImdoY3IuaW8vbW9kZWxzY29wZS9mdW5hc3ItbWNwOjAuMS4yIl19 Add to .cursor/mcp.json: ```json { "mcpServers": { "funasr": { "command": "docker", "args": [ "run", "-i", "--rm", "--mount", "type=bind,src={audio_directory},dst=/audio,readonly", "--mount", "type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope", "ghcr.io/modelscope/funasr-mcp:0.1.2" ] } } } ``` ### Claude Code Run in your terminal: ```shell claude mcp add funasr -- docker run -i --rm --mount 'type=bind,src={audio_directory},dst=/audio,readonly' --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope ghcr.io/modelscope/funasr-mcp:0.1.2 ``` ### Codex Run in your terminal: ```shell codex mcp add funasr -- docker run -i --rm --mount 'type=bind,src={audio_directory},dst=/audio,readonly' --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope ghcr.io/modelscope/funasr-mcp:0.1.2 ``` ### Antigravity Add to ~/.gemini/config/mcp_config.json: ```json { "mcpServers": { "funasr": { "command": "docker", "args": [ "run", "-i", "--rm", "--mount", "type=bind,src={audio_directory},dst=/audio,readonly", "--mount", "type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope", "ghcr.io/modelscope/funasr-mcp:0.1.2" ] } } } ``` ### Gemini CLI Run in your terminal: ```shell gemini mcp add funasr docker run -i --rm --mount 'type=bind,src={audio_directory},dst=/audio,readonly' --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope ghcr.io/modelscope/funasr-mcp:0.1.2 ``` ### OpenClaw In a terminal: Run openclaw mcp add funasr --command docker, with --arg before each argument (run -i --rm --mount 'type=bind,src={audio_directory},dst=/audio,readonly' --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope ghcr.io/modelscope/funasr-mcp:0.1.2) and --env NAME=value for each variable it needs. ### OpenCode Run in your terminal: ```shell opencode mcp add funasr -- docker run -i --rm --mount 'type=bind,src={audio_directory},dst=/audio,readonly' --mount type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope ghcr.io/modelscope/funasr-mcp:0.1.2 ``` ### Hermes Agent Add to ~/.hermes/config.yaml: ```json { "mcp_servers": { "funasr": { "command": "docker", "args": [ "run", "-i", "--rm", "--mount", "type=bind,src={audio_directory},dst=/audio,readonly", "--mount", "type=volume,src=funasr-mcp-cache,dst=/root/.cache/modelscope", "ghcr.io/modelscope/funasr-mcp:0.1.2" ] } } } ``` --- From Pluginboard (https://pluginboard.ai).