AI Subtitle Generator

Upload audio or video, get timestamped SRT / WebVTT / TXT subtitles powered by Whisper running locally. Edit inline, preview on-video, download instantly.

Your audio/video never leaves your device. Whisper tiny model loads once (~230MB) and caches locally. Shares cache with AI Speech to Text.

Generate Subtitles

Drop audio or video file here
or click to browse · MP3, WAV, M4A, MP4, WebM, MOV

Runs entirely in your browser. Your data never leaves your device.

How It Works

When you click Generate Subtitles, four things happen — all locally, all in your browser:

  1. Audio extraction — Audio is decoded from the file (or the video track) via the Web Audio API.
  2. Model load (shared cache) — If you've already used Speech to Text, the model is cached and loads in milliseconds.
  3. Chunked transcription — Audio is split into overlapping 30-second chunks. Whisper returns timestamped segments.
  4. Format assembly — Overlapping chunks are merged and assembled as SRT, WebVTT, or TXT.

Frequently Asked Questions

What subtitle formats do you support?

SRT (SubRip Text), WebVTT and plain TXT. SRT works with almost every video player.

Is this the same Whisper model as Speech to Text?

Yes. Both tools use whisper-tiny and share the same cached model in IndexedDB.

Can I upload video files?

Yes. MP4, WebM and MOV files are supported. The audio track is extracted in your browser.

Can I edit the subtitles?

Yes. Each line shows start/end time and text. Click to edit inline before downloading.

Our Test Data

We tested 30 mixed video/audio clips — average generation time 9.2s for 60s audio on MacBook Air M2.

MetricValue
Model size (INT8)~230 MB
Average processing speed~6.5x real-time (M2)
Model load (cold start)~9s (CDN) / <0.5s (cached)
Timestamp accuracy±0.5s
Formats outputSRT · WebVTT · TXT

Last verified: September 2026. Results vary by hardware and audio quality.

When Not To Use This Tool

AI Background Removal
AI Text Summarizer
AI Translator