MP3 to SRT, with an API call
Send an audio file or URL and download a ready-to-use .srt file. Cues are built from word-level timestamps and broken at natural pauses — two lines, readable length — not dumped one sentence per cue.
Your first transcription is free · then 5 minutes a month · no card
The whole integration
bash
# 1. start the job
ID=$(curl -s -X POST https://api.audiotranscribr.com/v1/transcriptions \
-H "x-api-key: $KEY" \
-d '{"url": "https://audiotranscribr.com/samples/clip-22-451-01.mp3"}' | jq -r .id) # a 1-minute sample we host; use any direct media URL
# 2. wait until it is done
until [ "$(curl -s https://api.audiotranscribr.com/v1/transcriptions/$ID -H "x-api-key: $KEY" | jq -r .status)" = "completed" ]; do sleep 3; done
# 3. download the subtitles
curl -sL "https://api.audiotranscribr.com/v1/transcriptions/$ID/result?format=srt" -H "x-api-key: $KEY" -o episode.srtFor a file on disk, leave out url: the response includes an upload link to PUT the file to. Works the same for M4A, WAV, FLAC, OGG and video files.
What the SRT looks like
The first cues of a real 76-minute recording (full file):
episode.srt
1 00:00:00,080 --> 00:00:06,800 You'll hear argument next in case 22451, Loper Bright Enterprises versus Raimondo. 2 00:00:06,800 --> 00:00:07,800 Mister Clement. 3 00:00:07,840 --> 00:00:12,640 Mister chief justice, and may it please the court, this case well illustrates the 4 00:00:12,640 --> 00:00:17,795 real world cost of Chevron, which do not fall exclusively on the chevrons of the 5 00:00:17,795 --> 00:00:21,475 world but injure small businesses and individuals as well.
You also get
- WebVTT with speaker voice tags, from the same job (
format=vtt). - Plain text, JSON with every word’s timestamp, and a formatted PDF.
- Speaker labels on every plan, including Free.
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 →
