WhipScribe has an API that takes a recording or link and returns SRT or VTT, with the 6,000-minute pack or Workspace. Packs: $4 for 300 minutes, $18 for 3,000, $32 for 6,000; Workspace $19 a month. Up to 10 hours or 5 GB per file. Measured turnaround: about 2 minutes per audio hour. 99 languages. Checked 2 Nov 2026.
How it works
POST a file, or a URL to fetch, with your API key. The response carries a job id.
Poll the job's status until it reads done. Most files finish in under a minute; an hour of audio takes a few.
GET the job's result with ?format=srt or ?format=vtt. The same job answers txt, docx and json.
The calls
Submit a link (use the file upload endpoint for local files):
curl -X POST https://whipscribe.com/api/v1/transcribe/url -H "X-API-Key: $KEY" -H "Content-Type: application/json" -d '{"url": "https://example.com/talk.mp4"}'
Check the job, then fetch subtitles:
curl https://whipscribe.com/api/v1/jobs/$JOB -H "X-API-Key: $KEY"curl "https://whipscribe.com/api/v1/jobs/$JOB/result?format=srt" -H "X-API-Key: $KEY" -o talk.srt
Parameter names, upload limits, error codes and the machine-readable description are in the API docs and at /openapi.json. Keys are created from your account once it has API access (the 6,000-minute pack or Workspace); agents and automation tools have their own guide at /agents.
What the output is
WEBVTT header.start, end and text, plus the detected language and duration.Usage is metered by the minute of audio against the same credit balance as the website, at the same price. API access comes with the 6,000-minute pack ($32) or Workspace ($19/month); smaller packs top up an account that already has it.
Sample output
1 00:00:34,680 --> 00:00:40,703 fourscore and seven years ago our fathers brought forth upon this continent 2 00:00:40,786 --> 00:00:43,709 a new nation conceived in in liberty, 3 00:00:43,839 --> 00:00:50,217 and dedicated to the proposition that all men are created equal. 4 00:00:50,300 --> 00:00:53,172 Now we are engaged in a great civil war, 5 00:00:53,293 --> 00:00:57,417 testing whether that nation, or any nation so conceived 6 00:00:57,500 --> 00:01:01,537 and so dedicated, can long endure. 7 00:01:01,620 --> 00:01:06,243 We are met on a great battlefield of that war we have come to dedicate 8 00:01:06,326 --> 00:01:11,249 a portion of that field as a final resting place for those who here gave 9 00:01:11,332 --> 00:01:14,240 their lives that their nation might live 10 00:01:15,360 --> 00:01:18,800 it is altogether fitting and proper that we should do this
WEBVTT 00:00:34.680 --> 00:00:40.703 fourscore and seven years ago our fathers brought forth upon this continent 00:00:40.786 --> 00:00:43.709 a new nation conceived in in liberty, 00:00:43.839 --> 00:00:50.217 and dedicated to the proposition that all men are created equal. 00:00:50.300 --> 00:00:53.172 Now we are engaged in a great civil war, 00:00:53.293 --> 00:00:57.417 testing whether that nation, or any nation so conceived 00:00:57.500 --> 00:01:01.537 and so dedicated, can long endure. 00:01:01.620 --> 00:01:06.243 We are met on a great battlefield of that war we have come to dedicate 00:01:06.326 --> 00:01:11.249 a portion of that field as a final resting place for those who here gave 00:01:11.332 --> 00:01:14.240 their lives that their nation might live 00:01:15.360 --> 00:01:18.800 it is altogether fitting and proper that we should do this
Real output, unedited: a public-domain LibriVox reading of the Gettysburg Address (2 min 41 s) transcribed here in October 2026, cut into cues exactly as the download does. The repeated word and the missing capitals are what came back; you would fix those on the transcript before downloading.
Before you rely on it
Each cue holds at most two lines of about 42 characters and stays on screen for one to seven seconds, breaking at the end of a sentence or clause where it can. The words are exactly the transcript's; only the breaks are chosen for the screen.
Cue times are taken from the recording itself, so the file lines up with the video or audio you uploaded. If you trim the start of the video afterwards, shift the cues by the same amount in your editor.
On public test recordings, about 7 words in 100 differed from the reference for clean English read speech, between 4 and 9 in 100 for Spanish, Portuguese, Russian, French and German, and about 21 in 100 for Hindi. Noisy rooms, music and crosstalk do worse. Method and every number: the benchmark.
Open the transcript, correct a misheard name or number on its line, and the SRT and VTT you download carry the correction with the timing unchanged.
You get the subtitle file. Fonts, colours, position and captions drawn into the picture are done in your video editor or player, which reads this file.
Up to 10 hours or 5 GB per recording. The box on this page takes files up to 500 MB; larger ones continue on the upload page. 99+ languages, detected automatically.
Pricing
The preview is free. When the full transcript needs a pack, one-time packs are $4 for 300 minutes, $18 for 3,000 minutes, $32 for 6,000 minutes. Credits never expire, which comes to about $0.32 to $0.80 per hour of audio. API access comes with the 6,000-minute pack ($32) or Workspace ($19/month). There is no free API tier and no separate API fee; smaller packs top up an account that already has access.
| Recording | $4 pack | $18 pack | $32 pack |
|---|---|---|---|
| 1,000 clips of one minute | $13.33 | $6.00 | $5.33 |
| 100 one-hour recordings | $80.00 | $36.00 | $32.00 |
| One 10-hour archive file | $8.00 | $3.60 | $3.20 |
Figures are the share of a pack each recording uses. A button opens secure checkout for that pack. Every export format is included; full details on the pricing page.
FAQ
Yes. Submit a file or URL, wait for the job to finish, and request the result with format=srt or format=vtt. TXT, DOCX and JSON are available from the same job.
API access comes with the 6,000-minute pack ($32, about $0.32 per hour of audio) or Workspace ($19/month). It draws on the same credits as the website, with no separate API fee and no free API tier.
No. Timing is per phrase: each cue or JSON segment has a start and an end time.
Up to 10 hours or 5 GB per file.
No. The API transcribes recorded files and finished streams. It is not a live captioning service.
Every page in this set uses the same upload box and the same export. All subtitle pages
Drop a file, download the SRT, and see whether the cue shape fits your pipeline. Free preview; API access with the 6,000-minute pack ($32) or Workspace.