GUI Hub
For Claude, Cursor, VS Code & other MCP clients

Can Claude transcribe an audio or video file?

Not on its own. a chat AI can't run programs or write files on your computer. With the GUI Hub Essentials MCP server installed, Claude (Desktop or Code), Cursor, VS Code and other MCP clients can transcribe audio or video to text locally: the assistant calls the transcribe_transcribe tool, which runs Whisper (sherpa-onnx) on your machine. Files are not uploaded.

Set it up (2 minutes)

  1. Claude Code / Cursor / VS Code / Windsurf: add the MCP server
    npx -y https://guihub.cc/mcp.tgz --product=essentials
    Claude Code: claude mcp add gui-hub-essentials -- npx -y https://guihub.cc/mcp.tgz --product=essentials
  2. Claude Desktop: download the one-file extension and double-click it.
  3. No AI? GUI Hub Essentials is also a point-and-click desktop app.

Then ask

“Transcribe meeting.m4a and summarize the decisions.”

What the AI gets

transcribe_transcribe — Transcribe an audio or video file on the user's computer (mp3, m4a, wav, mp4, mov, …) to text with Whisper, offline. Returns the full transcript (optionally with [hh:mm:ss] timestamps) and can also save it to a .txt file (`out`). Set `translate` to get an English translation instead. Use this whenever the user wants a recording, voice memo, meeting or video turned into text, notes or a summary.

InputType
input*string
languagestring (, en, es, fr, de, it)
translateboolean
timestampsboolean
outstring

Cost

Free to install; each tool has 3 free uses. Then $9 once for all of GUI Hub Essentials (no subscription). The tool tells the assistant when free uses run out and how to unlock.

Powered by Whisper (sherpa-onnx) (Apache-2.0 (Whisper model: MIT)), the official release, verified by SHA-256. GUI Hub is independent and not affiliated with Whisper (sherpa-onnx), Anthropic, Cursor or Microsoft.

Other things your AI can do with GUI Hub