Auto subtitles generator
AI-generated captions for any video or audio file — accurate, editable, and free.
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.
Captions boost watch time and accessibility, but manually typing them out is slow. This uses OpenAI's Whisper speech-recognition model, running entirely on your device, to generate a timestamped transcript in the time it takes to watch the clip once. Fix any misheard words directly in the transcript editor, then export subtitle files or burn the captions straight into the video.
Frequently asked questions
How accurate is the AI transcription?
Whisper is highly accurate on clear speech in quiet audio — expect a few misheard words on accented, overlapping, or noisy speech, which is why the transcript is editable before you export.
Does this cost anything or have a time limit?
No — it's free with no per-minute cap. The only cost is your own device's processing time, since everything runs locally.
Do I need to be online?
You need an internet connection the first time to download the speech model (cached in your browser after that); the transcription itself runs fully offline once the model is loaded.
Is my video uploaded to a server for transcription?
No — the AI model runs inside your browser via WebAssembly/WebGPU. Your file never leaves your device.