English audio to editable text
Load a short English recording, transcribe locally, review the segment text, then export TXT. TXT contains only edited speech text, not timings. No video extraction or live microphone path is included.
GIVE YOUR WORDS A LITTLE ROOM
From spoken words.
To something you can share.
Turn a short English recording into editable captions, right here on your device.
AI captions are drafts. Review names, numbers, words, and timing. Segment timestamps are approximate, not word alignment.
01 / LOCAL MODEL
Small model. Explicit choices.
Whisper tiny.en · English only · q8 CPU/WASM · size loading model + runtime assets.
Whisper MIT; ONNX conversion/runtime notices included. License · How local inference works
Tested on desktop Chrome with 16 GB RAM; observed browser working set about 1.4 GB. Low-memory/mobile devices and WebGPU are unvalidated.
Asset caching is opt-in. Audio/captions stay transient.
Recording & captions
A recording is a good place to start.
WAV, MP3, M4A, OGG, WebM audio, FLAC · browser dependent · 50 MiB / five minutes max
Your words will find their place here.
Choose audio, load the model, then transcribe.
You stay in control of the final captions.
Choose a short recording. Nothing is uploaded.
03 / TAKE IT WITH YOU
Review it. Make it yours.
Text edits and valid timing adjustments are used in the export. Times must be ordered, nonoverlapping, and inside the recording.
Good captions begin with a careful listen.
One English model, one inference worker. Audio is decoded locally, downmixed/resampled to 16 kHz, then processed in overlapping 30-second windows. Silence below an RMS threshold of 0.0001 is skipped; quiet speech can be missed, and hallucinations can still occur.
Load model fetches assets from this host. Cache assets explicitly stores only reusable model/runtime files for offline inference in an already loaded page; reopening the site offline is not guaranteed. Clear session unloads the model and clears audio/caption references. Remove model cache deletes only this app’s opt-in asset cache.
Five-minute limit is provisional. CPU speed and RAM vary; keep recordings short on constrained devices. Unsupported decoding, WASM, or model errors never send audio to a cloud service.