Transcribe a video from a link
Downloads a YouTube, TikTok, Instagram, Twitch or Kick video, adds it to your library and transcribes it, charged like POST /transcriptions by the video's length. Poll GET /transcriptions/{transcriptionId} until ready. 400 UNAVAILABLE when the link cannot be read (private, removed, unsupported site), 502 UNAVAILABLE when the download failed and can be tried again, 503 SERVICE_UNAVAILABLE when downloads are paused for a moment.
apiKeyX-Api-Key<token>- body
url*stringLink to the video
length <= 2048speaker_labels?booleanIdentify who is speaking on each cue. Costs more. Default false.
source_language?stringSpoken language, e.g. pt. Omit to auto-detect.
Response for status 202
application/json- response
id*stringTranscription id; poll GET /transcriptions/{transcriptionId}
status*"processing""processing"credits_charged*numbercurl -X POST 'https://api.cut.pro/api/v1/transcriptions/import' \ -H 'Content-Type: application/json' \ -d '{ "url": "string"}'{ "id": "string", "status": "processing", "credits_charged": 0}Transcribe a media file POST
Starts a transcription for a media file you uploaded via `POST /transcriptions/upload`. Credits are charged per minute of audio, plus a surcharge when `speaker_labels` is requested. Check the balance at `GET /balance` first. Responds `202` with `status: processing` when the ASR worker was dispatched: poll `GET /transcriptions/{transcriptionId}` until `status` is `ready` (or `failed` / `no_speech`), then fetch the text. Responds `200` when nothing had to run. That happens when the same audio was already transcribed (the transcript is shared per media, so a re-run is a cache hit and `credits_charged` is `0`), or when the audio is silent, which comes back as `no_speech` and is not billed. Passing a `media_id` that is already in your library re-runs it. That is how a transcript created without diarization is upgraded: ask again with `speaker_labels: true` and the audio is reprocessed, because the speaker column cannot be added after the fact.
Get transcription status GET
Returns the current state of a transcription job. Poll every **5–10 seconds** while `status` is `processing`. Once `status` is `ready`, fetch the text with `GET /transcriptions/{transcriptionId}/transcript` (JSON cues) or `GET /transcriptions/{transcriptionId}/download` (SRT, VTT or plain text).