Generate captions free
The free alternative to captioning tools that charge per minute or per month.
More accurate, slower — recommended
The first run downloads the speech model to your browser (cached after that). Best on desktop — mobile devices may be slower.
Drop a video or audio file to transcribe
or click to browse
How it works
Drop a video or audio file in. WavyVid decodes the audio track right in your browser.
An AI speech-recognition model (Whisper, running fully on-device via WebAssembly/WebGPU) transcribes the audio into timestamped text.
Edit the transcript if needed, then export as .srt/.vtt, or burn the captions directly into your video.
Most auto-captioning tools meter you by the minute or lock accurate models behind a subscription. This runs the transcription model in your own browser instead of a metered cloud API, so there's no per-minute cost and no limit on how many files you caption.
Frequently asked questions
Is this really free, unlike Kapwing/Veed/Descript captions?
Yes — no subscription, no per-minute limit, no watermark on exported captions.
Can I style the captions before burning them in?
Burned-in captions use a clean, readable default style (white text, dark outline). For more control, export the SRT/VTT and style it in your video editor.
How long does it take to caption a video?
Roughly real-time or faster on a modern laptop with GPU acceleration; slower (but still functional) on CPU-only devices.
Do I need an account?
No — no sign-up, no email required.