Captions for video & audio
Captions for your videos, without the typing.
Upload a video or audio file. Captionbench listens right in your browser and writes out timed captions you can edit and download. Free, no account needed — and your files are never uploaded anywhere.
Three steps
From recording to captions in minutes
01
Drop in your file
Video or audio, up to 3 minutes. It stays on your device — nothing is sent to a server.
02
Read and tidy up
Every line comes with its timestamp. Click a line to hear that moment, fix a word, split or merge lines.
03
Download and publish
Take SRT for YouTube, VTT for the web, or plain text for anything else. Copy it with one click.
A look inside
What the editor feels like
Each caption sits on its own row with real start and end times. This is a preview — the live tool works exactly like this.
Questions
Asked often
Is it really free?
Yes. Transcription runs on your own device using an open model, so there is nothing for us to charge you for. Files up to 3 minutes and 25 MB are free, with SRT, VTT and TXT downloads included.
Are my videos uploaded to your servers?
No. Your file never leaves your browser — it is decoded and transcribed locally on your device. Our privacy policy says exactly this, in plain words.
Which languages are supported?
English, Hindi and Urdu, plus automatic detection if you are not sure. You can pick the language before transcription starts.
How long does transcription take?
Roughly two to four minutes for each minute of audio on a typical laptop. The first visit downloads the transcription model once (about 40–150 MB); afterwards it is cached and starts instantly.
Can I upload the captions to YouTube?
Yes — the SRT download follows YouTube's format exactly (numbered blocks with millisecond timestamps). Upload it in YouTube Studio under Subtitles.
Ready when your next video is.
No sign-up, no watermarks, no uploads. Just captions.