whisper-mcp

Local Whisper transcription, exposed as an MCP server — so any MCP client (Claude Desktop, Claude Code, etc.) can transcribe audio/video files, generate .srt subtitles, and burn captions into a video, directly as tool calls. No cloud API, no manual "run a script and go read the output file" step.

Built on faster-whisper for inference and ffmpeg for audio extraction / caption burn-in.

Architecture

MCP client (Claude, etc.) --stdio--> whisper-mcp server --> faster-whisper (Whisper model)
                                                        \--> ffmpeg (audio extract / burn-in)

The server keeps loaded Whisper models cached in memory for the life of the process, so repeated tool calls in one session don't re-pay model load time.

Related MCP server: Whisper MCP Server

Tools

Requirements

• Python 3.10+

• ffmpeg on PATH

• Optional: a CUDA-capable GPU (falls back to CPU automatically)

Install & run

pip install -e ".[dev]"
whisper-mcp

Or, zero-install:

uvx --from git+https://github.com/Chain-P/whisper-mcp whisper-mcp

Configure in an MCP client

Add to your client's MCP config (e.g. Claude Code's .mcp.json or Claude Desktop's claude_desktop_config.json):

{
  "mcpServers": {
    "whisper": {
      "command": "whisper-mcp"
    }
  }
}

Then ask the client to transcribe a file, e.g. "transcribe samples/podcast_clip.mp4 and give me the SRT."

Development

pip install -e ".[dev]"
ruff check .
pytest                        # unit tests only
pytest -m integration         # + real transcription against a sample file

Roadmap

• Speaker diarization (pyannote.audio / whisperx) for multi-speaker labeling in the SRT output.

• MCP progress notifications for long transcriptions.

• A resource exposing recent transcript history.

License

MIT