Convert Video to SRT in Your Browser
Turn the spoken audio in a video into editable subtitles. Run Whisper on your own device, then download SRT, VTT or plain text.
AI model will be downloaded once and cached in your browser. Download size depends on the model and backend; actual size appears during download.
Checking browser capabilities… · Checking model cache…
How it works
- Choose a video and a Whisper model.
- Download the model once, then transcribe the audio on your device.
- Review the text and download your subtitles.
Key features
- Local video to SRT converter with Tiny and Base models.
- WebGPU acceleration with automatic WASM fallback.
- Editable text and SRT, VTT and TXT downloads.
Supported formats
MP4, WebM and MOV when their audio codec can be decoded by your browser. Up to 30 minutes per file in this MVP.
Private by design
Your files stay on your device. Media is processed locally and is not uploaded to our server. Whisper runs in your browser; model downloads come from model hosting or a CDN.
Frequently asked questions
Is my video uploaded?
No. Your media is read and processed locally. The browser downloads AI model files from a model host.
How accurate are the subtitles?
Accuracy depends on speech, background noise and language. Review the generated text and timing before use.
Can I use it without WebGPU?
Yes. The tool uses a WASM fallback when WebGPU is unavailable. It can be slower, particularly on mobile devices.