Preview
No video loaded yet
Drop a video, or click to upload
MP4 or WebM with an audio track works best. Everything happens locally — nothing is uploaded anywhere.
Loading…
Caption track
00:00 / 00:00
Generate captions to see the caption track here.
Speech recognition runs locally using a small Whisper model (via transformers.js). The first generation downloads the model once; your browser caches it for next time. Longer videos are processed in 5-minute segments for better performance.
Liked Captionly? Buy me a coffee to help me keep it free and ad-free. Thank you!