Burn in subtitles
Hardcode captions directly into the video frame — no separate subtitle file needed.
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.
Burned-in ("open") captions always show, regardless of the platform or player's subtitle support — useful for social clips where viewers watch on mute, or platforms with inconsistent .srt handling. WavyVid transcribes your video with AI, lets you fix any errors, then re-encodes the video with the captions rendered directly onto the picture.
Frequently asked questions
What's the difference between burned-in and a separate SRT file?
A separate SRT can be toggled on/off and styled by the viewer's player; burned-in captions are permanently part of the video image and always visible, which is more reliable on platforms like Instagram/TikTok where many viewers watch muted.
Does burning in captions re-encode the whole video?
Yes — rendering text onto the picture requires re-encoding the video stream (audio is copied through unchanged), so processing takes a bit longer than a straight transcription.
Can I edit the captions before burning them in?
Yes — review and edit the AI-generated transcript first, then burn in the corrected version.
Is there a watermark on the output video?
No — the exported video has no watermark.