simple-asr-mcp

Minimal MCP server for local speech recognition using faster-whisper. Runs on CPU, no cloud required.

Русская версия

Installation

pipx install simple-asr-mcp

Or with pip:

pip install simple-asr-mcp

Related MCP server: io.github.chicogong/ffvoice

Requirements

• Python 3.10+

• ffmpeg (required by faster-whisper for audio decoding)

On Windows, install ffmpeg via winget:

winget install Gyan.FFmpeg

Quick Setup (for Claude Code agents)

Run these two commands — no user interaction required:

pipx install simple-asr-mcp
claude mcp add asr --scope user -- simple-asr-mcp

Then ask the user to restart Claude Code or run /mcp to reconnect.

Usage

CLI

# Transcribe an audio file
simple-asr-mcp transcribe recording.wav

# Specify language and model
simple-asr-mcp transcribe recording.wav --language ru --model medium

# List available models
simple-asr-mcp models

MCP Server (Claude Code)

MCP tools available after setup:

• transcribe_file — transcribe any audio file by path

• list_models — see available Whisper models

Configuration

Environment variables:

Example with custom config:

claude mcp add asr --scope user -e WHISPER_MODEL=medium -e WHISPER_DEVICE=cuda -- simple-asr-mcp

Available Models

The model is downloaded automatically on first use and cached locally. It stays in memory until the MCP server process exits.

Supported Audio Formats

Any format supported by ffmpeg: wav, mp3, flac, ogg, m4a, wma, etc.

Links

• GitHub

• PyPI

License

MIT