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 make an audiogram from my podcast?

Not on its own. AI assistants can read a transcript and choose the best moment, but they can’t hear the audio, time captions to it or render a video with a waveform — that normally takes an audiogram service or a video editor. With the GUI Hub Audio MCP server installed, Claude (Desktop or Code), Cursor, VS Code and other MCP clients can turn a podcast or audio clip into a video with a waveform and captions (an audiogram) locally: the assistant calls the clips_audiogram tool, which runs FFmpeg + Whisper 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 clips_audiogram --input /path/to/input.mp3 --cover /path/to/input.jpg --start "…" --end "…" --out /path/to/output.mp4

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

Then ask

“Find the best 40 seconds of episode12.mp3 and make a vertical audiogram with cover.jpg for Instagram.”

What the AI gets

clips_audiogram — Make an audiogram (MP4) on the user's computer, offline: the part of an audio file (podcast, interview, voice note) from `start` to `end` becomes a video with the `cover` image, an animated waveform and burned-in captions timed to the speech (Whisper). Use when the user wants to share audio on Instagram, TikTok, YouTube Shorts, LinkedIn or X, which need video. To pick a moment, get the transcript first (transcribe_transcribe), choose a self-contained 20–60 s passage, then call this; one call per clip. `shape`: vertical (Reels/TikTok/Shorts), square (feeds) or landscape (YouTube/X).

InputType
input*string
cover*string
start*string
end*string
shapestring ([0:v]split[c0][c1];[c0]scale=1080:1920:force_original_aspect_ratio=increase,crop=1080:1920,boxblur=30:2,eq=brightness=-0.3[bg];[c1]scale=860:860:force_original_aspect_ratio=decrease[cv];[1:a]aformat=channel_layouts=mono,volume=3,showwaves=s=1080x240:mode=cline:scale=sqrt:draw=full:rate=30:colors=white,format=rgba[w];[bg][cv]overlay=(W-w)/2:240[b1];[b1]drawbox=x=0:y=1160:w=1080:h=240:color=black@0.45:t=fill[b2];[b2][w]overlay=0:1160,format=yuv420p[v0], [0:v]split[c0][c1];[c0]scale=1080:1080:force_original_aspect_ratio=increase,crop=1080:1080,boxblur=30:2,eq=brightness=-0.3[bg];[c1]scale=560:560:force_original_aspect_ratio=decrease[cv];[1:a]aformat=channel_layouts=mono,volume=3,showwaves=s=1080x180:mode=cline:scale=sqrt:draw=full:rate=30:colors=white,format=rgba[w];[bg][cv]overlay=(W-w)/2:50[b1];[b1]drawbox=x=0:y=640:w=1080:h=180:color=black@0.45:t=fill[b2];[b2][w]overlay=0:640,format=yuv420p[v0], [0:v]split[c0][c1];[c0]scale=1920:1080:force_original_aspect_ratio=increase,crop=1920:1080,boxblur=30:2,eq=brightness=-0.3[bg];[c1]scale=640:640:force_original_aspect_ratio=decrease[cv];[1:a]aformat=channel_layouts=mono,volume=3,showwaves=s=1000x260:mode=cline:scale=sqrt:draw=full:rate=30:colors=white,format=rgba[w];[bg][cv]overlay=120:220[b1];[b1]drawbox=x=860:y=300:w=1000:h=260:color=black@0.45:t=fill[b2];[b2][w]overlay=860:300,format=yuv420p[v0])
languagestring (, en, es, fr, de, it)
out*string

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 FFmpeg + Whisper (GPL (FFmpeg static build), MIT (Whisper model), Inter font: OFL-1.1), the official release, verified by SHA-256. GUI Hub is independent and not affiliated with FFmpeg + Whisper, Anthropic, Cursor or Microsoft.

Other things your AI can do with GUI Hub