Leaving slide mode.

Whisper Live Captioning Demo

Accessible HTML Presentation with Real-Time Transcription

Live captions via Web Speech API (browser, no install) or Whisper.cpp (local, high accuracy)

Caption Listener Status

How to Start the Caption Listener

  1. Open a terminal in your project root.
  2. Set WHISPER_BIN and WHISPER_MODEL environment variables if needed.
  3. Set WHISPER_LANGUAGE to an ISO 639-1 code (e.g. fr, de, ja) if not speaking English. Omit for auto-detection.
  4. Run npm run dev:whisper to start the caption listener and transcript writer.
  5. Reload this page. The red circle (🔴) recording indicator will appear when the transcript is available.

If you prefer, you can use npm run dev:transcript to mirror a text file to JSON instead.

Captioning Options

GitHub Pages Alternatives

Whisper.cpp needs a local binary. For static hosting, consider these options:

Web Speech API

Demo Iframe

If the demo doesn't load, open it directly: whisper-demo/index.html

Live Transcript

Polling /presentations/whisper-demo/transcript.json every second.

Combined

Demo

Transcript