Free during launch: every app and tool is unlimited — no account, no card. Purchases open soon (then $9 once). Download · Free browser tools
GUI Hub
For Claude, Cursor, VS Code & other MCP clients

Can Claude tell who said what in a meeting recording?

Not on its own. chat apps like Claude Desktop and ChatGPT can't run programs or write files on your computer. (Coding agents can install the underlying program themselves; GUI Hub saves that setup with tested builds, models and settings.) With the GUI Hub Audio MCP server installed, Claude (Desktop or Code), Cursor, VS Code and other MCP clients can find who spoke when in a meeting or interview recording locally: the assistant calls the speakers_diarize tool, which runs pyannote + TitaNet (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=audio
    Claude Code: claude mcp add gui-hub-audio -- npx -y https://guihub.cc/mcp.tgz --product=audio
  2. Claude Desktop: download the one-file extension and double-click it.
  3. No AI? GUI Hub Audio is also a point-and-click desktop app.

Agent with its own computer?

Grok Bot, ChatGPT dots, Claude Duet, OpenClaw, Manus or Codex can run it directly — no MCP needed:

npx -y https://guihub.cc/cli.tgz run speakers_diarize --input /path/to/input.mp3

Options: npx -y https://guihub.cc/cli.tgz info speakers_diarize · skill file: SKILL.md · more for agents

Then ask

“Transcribe board-meeting.m4a with speaker labels and list each person’s action items.”

What the AI gets

speakers_diarize — Detect who is speaking when in an audio or video recording on the user's computer (speaker diarization, offline): returns lines like '[00:01:05 → 00:01:20] Speaker 2'. Use for meetings, interviews, podcasts and calls when the user wants speaker labels or 'who said what' — run transcribe_transcribe with timestamps as well and match the times to label each line of the transcript with its speaker. Set `speakers` if the number of people is known.

InputType
input*string
speakersstring (, 2, 3, 4, 5, 6)
outstring

Cost

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

Powered by pyannote + TitaNet (sherpa-onnx) (Apache-2.0 (pyannote segmentation: MIT; TitaNet: CC-BY-4.0)), the official release, verified by SHA-256. GUI Hub is independent and not affiliated with pyannote + TitaNet (sherpa-onnx), Anthropic, Cursor or Microsoft.

Other things your AI can do with GUI Hub