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 into the tool — nothing is uploaded, WavyVid decodes the audio track directly in your browser.
OpenAI's Whisper speech-recognition model, running on-device via WebAssembly/WebGPU, transcribes the audio into timestamped captions in roughly the time it takes to watch the clip once.
Review and fix any misheard words in the editable transcript, then export as SRT or VTT, or burn the captions directly into the video.
When you'd use this
- You're posting to TikTok, Instagram, or LinkedIn, where most viewers watch with the sound off and won't stick around without captions.
- You want your video to be more accessible and easier to find in search, since captions let platforms index every word you say.
- You have a backlog of clips to caption and don't want to pay a subscription tool that caps you by the minute.
Frequently asked questions
How accurate are AI-generated subtitles?
Very, on clear audio — Whisper typically lands in the 90%+ range under good recording conditions, similar to what most paid subtitle tools advertise. Accuracy drops with heavy background noise, strong accents, or multiple speakers talking over each other, which is exactly why the transcript stays editable before you export.
Is there a free subtitle generator with no watermark?
Yes — this one. There's no watermark on burned-in captions, no per-minute cap, and no account required, because the transcription model runs in your own browser instead of a metered cloud service you'd otherwise be paying to subsidize.
What's the difference between SRT and VTT subtitle files?
SRT is the simpler, more universally compatible format — plain text with timestamps, accepted almost everywhere. VTT (WebVTT) adds styling and positioning options built for HTML5 video players. Export SRT if you're unsure which your platform expects; export VTT if you specifically need web-native styling.
Can I edit the subtitles before exporting?
Yes — every line of the AI-generated transcript is editable directly in the browser. Fix a misheard word, adjust a timestamp, or split a line, then export once everything reads correctly.
Do I need to upload my video to generate subtitles?
No — that's the core difference from most subtitle generators. The Whisper model downloads once and then runs entirely on your device; your video file is never sent to a server, transcribed remotely, or stored anywhere outside your browser.