No upload · No size limit · No watermark · No signup
Generate subtitles from audio or video with Whisper
Drop an audio or video file and an in-browser Whisper AI model transcribes it into timestamped subtitles — entirely locally in your browser, so nothing is ever uploaded. Export the result as SRT or VTT when you're done.
How it works
- Drop an audio or video file. It stays on your device.
- Pick a model and generate captions — the first run downloads the model once.
- Read the transcript, then download it as .srt or .vtt.
Frequently asked questions
Is my audio or video uploaded to a server?
No. The Whisper speech-recognition model runs entirely in your browser via WebAssembly or WebGPU — your file is never uploaded, and once the model is cached it even works offline.
Why does the first transcription take a while?
The first run downloads a small Whisper model (tens of megabytes) and caches it in your browser. Every transcription after that starts instantly from the cache, even offline.
Can I fix mistakes or resync the timing afterward?
Yes. Export the transcript as .srt or .vtt, then open the Subtitle Editor to correct text, tweak timestamps or shift every cue at once.
Which languages and file types are supported?
The bundled models are English-only Whisper checkpoints, tuned for speed and accuracy on English speech. Both audio (MP3, WAV, M4A, OGG) and video (MP4, WebM) files work — the video's audio track is transcribed.