POST /audio/transcriptions

Live
Transcribe multipart or referenced audio.
Open in ChatGPT
(opens in new tab)Last verified: 2026-08-11

Endpoint

POST /audio/transcriptions
Transcribe multipart or referenced audio. The base URL is https://api.modelrush.ai/v1.

Request

model and file/audio; optional language, enable_itn, region. Send Authorization: Bearer $MODELRUSH_API_KEY for authenticated routes and Content-Type: application/json for JSON bodies.

Response

text, model, modelrush_region, generation_request_id. Preserve returned request or generation identifiers. Generated outputs and their Provider file references are removed from the ModelRush database 24 hours after request completion; download anything you need to keep.

Errors

Invalid inputs return a 4xx response with a structured error. A 403 with adult_attestation_required, portrait_rights_attestation_required, or person_rights_confirmation_required must be resolved by the account user and must never be retried automatically. Retry 429 according to Retry-After; retry 5xx failures only with a bounded backoff policy.
PreviousPOST /audio/speech
NextGET or DELETE /predictions/:id