FunASR — Claude Code MCP server: what it does, how to install
FunASR turns local audio files into text through an MCP tool. Use it to transcribe a meeting or voice memo from your AI coding client.
claude mcp add mcp_server -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2What FunASR does
The server exposes transcribe_audio, which takes an audio file path and returns recognized speech as text. It accepts WAV, MP3, FLAC, M4A, and OGG files. You can let it identify the language or provide a code such as en or yue. Longer recordings are split into speech segments; timestamps appear when the selected model provides them.
Inference runs locally, so an API key is not needed. Choose a model with FUNASR_MODEL and a device with FUNASR_DEVICE; supported options include cpu, cuda, and mps. CPU is the default, so check that this setting fits your machine. For a Python setup, install funasr; Claude Code can also launch the published Docker image with the command below.
What it helps with
- transcribe a meeting recording
- turn a voice memo into text
- extract speech from an MP3 or FLAC file
- split a long recording into speech segments before recognition
Example prompts for the agent
- Transcribe the meeting recording at
~/Downloads/meeting.wav. - Turn
~/voice_note.m4ainto text. - Tell me what is said in
/path/to/interview.mp3.
How to install FunASR
Platform CLI
claude mcp add mcp_server -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2Platform CLI
codex mcp add mcp_server -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2Config file
{
"mcpServers": {
"mcp_server": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2"
]
}
}
}Config file
{
"servers": {
"mcp_server": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/modelscope/funasr-mcp:0.1.2"
]
}
}
}Platform CLI
gemini mcp add mcp_server docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2Step 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 FunASR
How do I install FunASR in Claude Code?
Run claude mcp add mcp_server -- docker run -i --rm ghcr.io/modelscope/funasr-mcp:0.1.2. This registers the MCP server through Docker.
What does FunASR do?
It recognizes speech in a local audio file and returns text. Longer recordings are divided into speech segments.
Does FunASR require an API key?
No. Recognition runs locally. Set the device with FUNASR_DEVICE; the available choices are cpu, cuda, and mps.
