Online Free · No Upload · Whisper AI

Video to SRT Subtitles

Upload a video and get timed SRT subtitles powered by OpenAI Whisper — running entirely in your browser. WebGPU accelerates transcription when your browser supports it.

The first run downloads the Whisper tiny model (~40 MB). Long videos may take several minutes to transcribe.

Voice to MP3 Compress Video

Loading tool...

How it works

Your video's audio track is extracted with ffmpeg.wasm, then fed to the Xenova/whisper-tiny model via transformers.js. Timestamps are formatted as standard SRT and you can download the .srt file for use in video editors, YouTube, or VLC.

Privacy

Nothing is uploaded to a server. Audio extraction, model inference, and SRT generation all happen on your device. The model weights are cached in your browser after the first download.

Common questions

Why is the first run slow?

The Whisper model (~40 MB) downloads from Hugging Face on first use and is cached locally. Subsequent runs skip the download.

Can I pick the language?

Whisper auto-detects language. For mixed-language videos, accuracy may vary — use clear audio for best results.

Related tools & guides

Video to Live Photo

Free online converter

MP4 to Live Photo