Captions for your video player, from one API call
Send an MP4, MOV or WebM (file or URL) and get a .vtt file you can drop straight into an HTML5 <track> element — with speaker voice tags — plus SRT for everything else.
Your first transcription is free · then 5 minutes a month · no card
Generate the captions
bash
curl -s -X POST https://api.audiotranscribr.com/v1/transcriptions \
-H "x-api-key: $KEY" \
-d '{"url": "https://audiotranscribr.com/samples/clip-22-451-01.mp3"}' # any audio or video URL; this sample is hosted by us
# poll GET /v1/transcriptions/{id} until "status": "completed", then:
curl -sL "https://api.audiotranscribr.com/v1/transcriptions/$ID/result?format=vtt" -H "x-api-key: $KEY" -o webinar.vtt
html
<video controls src="webinar.mp4"> <track kind="captions" src="webinar.vtt" srclang="en" label="English" default> </video>
No need to extract the audio first — send the video as it is.
What the VTT looks like
From a real recording (full file):
webinar.vtt
WEBVTT 00:00:00.080 --> 00:00:06.800 <v Speaker 1>You'll hear argument next in case 22451, Loper Bright Enterprises versus Raimondo. 00:00:06.800 --> 00:00:07.800 <v Speaker 1>Mister Clement. 00:00:07.840 --> 00:00:12.640 <v Speaker 2>Mister chief justice, and may it please the court, this case well illustrates the 00:00:12.640 --> 00:00:17.795 <v Speaker 2>real world cost of Chevron, which do not fall exclusively on the chevrons of the
Details
- Cues are at most two lines and a few seconds long, timed from word-level timestamps.
- Each cue carries a
<v Speaker>voice tag you can style with CSS. - The same job also produces SRT, plain text, JSON and a PDF transcript.
Pricing
Your first transcription is free, then 5 minutes a month. Paid plans start at $9 a month for 10 hours of audio. All plans →