Kavio

Local AI captions for any video, running entirely in your browser. Whisper-grade transcription, word-level timestamps, multiple caption styles, inline transcript editing, video export with burned-in captions, and SRT or VTT delivery. No uploads. No accounts. No servers.

Kavio requires JavaScript and a modern browser with WebGPU support (Chrome, Edge, Arc, or Brave) to run the speech model on your device.