Business APIs › Captioning API for recorded video — and what

Captioning API for recorded video — and what we do not do live

If you need captions on recordings, this is a single call. If you need them streaming in real time, we are the wrong tool and this page says so.

Short answer

Whipscribe transcribes recorded audio and video, fast — about two minutes for an hour — but it is not a streaming ASR service. There is no socket to attach to a live feed.

Side by side

ElsewhereWhipscribe
Recorded video captions—Yes
Streaming / real-time—No — use a streaming ASR vendor
Turnaround—~2 min per audio hour
Formats—srt · vtt · txt · json · docx

What we do

Post a finished recording, get caption tracks in SRT or VTT timed to the speech. For webinars, lectures, and anything published after the fact, that is the whole job, and it is cheaper and more accurate than real-time because the model sees the entire file.

What we do not do

We do not stream partial hypotheses over a socket while someone is still talking. If your requirement is captions appearing on screen during a live event, you want a streaming ASR vendor, not this API. Saying so here saves you an integration.

The case in between

Most teams who search for live captioning actually need captions shortly after the event, not during it. A recording that finishes at 3:00 has captions before 3:05, which is usually what the requirement was.

Accessibility obligations

Post-event captioning is what most accessibility policies actually require, because the artefact under obligation is the published recording.

What it costs

Rate$0.0053 / min
Per audio hour$0.32
10 hours of audio$3.20
CreditsNever expire

$32 per 6,000 minutes — about $0.32 an audio hour — and credits never expire.

Why run it here

No subscription to size wrongCompeting transcription tools sell $25–$65 monthly plans with a minute cap that resets whether you used it or not. Credits here are bought once and do not expire, so a quiet month costs nothing and a backlog run does not need an upgrade.
Your audio is not sent to a third-party modelTranscription runs on our own servers in our own private cloud. Nothing is forwarded to OpenAI or any other vendor's API, which is usually the blocking question when the recordings are customer calls or unreleased material.
One job, every formattxt, json, srt, vtt and docx all come from the same job id. Re-submitting a file per format is the most common way teams pay several times for one transcription.
Built to be retriedIdempotency-Key means an automation platform's automatic retry returns the original job instead of billing a second one. Every no-code platform retries; most transcription APIs charge you for it.

Wire it into

Zoomdownload_url needs the event download_tokenmeetingsYouTubeauto-captions have no punctuation or speakersvideo platformAmazon S3presigned URLs expire — grant a scoped role for standing pipelinesstorage
Try the quality free, then wire it up

In the web app the opening minutes are a free preview, and a pack from $4 (300 minutes) transcribes the rest — that is how to check accuracy on your own audio before writing any code. The API has no recurring free tier: without a key you can run 3 sample transcriptions a day, each returning a preview, and keys come with the 6,000-minute pack ($32) or Workspace ($19/month). $32 per 6,000 minutes — about $0.32 an audio hour — and credits never expire.

Transcribe a file free →Create an API keyAPI referenceIntegrationsAutomations

Not writing code?

If you just need recordings transcribed: see our transcription service with prices and turnaround.