POST /audio/speech

Live
Synthesize WAV speech from text.
Open in ChatGPT
(opens in new tab)Last verified: 2026-08-11

Endpoint

POST /audio/speech
Synthesize WAV speech from text. The base URL is https://api.modelrush.ai/v1.

Request

model, input, voice; optional language_type, region. Send Authorization: Bearer $MODELRUSH_API_KEY for authenticated routes and Content-Type: application/json for JSON bodies.

Response

audio/wav body plus generation, model, and region headers. 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.
PreviousGET /videos/generations/:id
NextPOST /audio/transcriptions