Get a text-to-speech batch | FormantAI

Returns the batch’s status and, once it finishes, a time-limited link per rendered clip. Poll until status is completed or failed; both are terminal. Every poll mints fresh links. A batch is scoped to the workspace that submitted it and stops resolving one hour after submission.

Authentication

AuthorizationBearer

Bearer authentication of the form Bearer <token>, where token is your auth token.

Path parameters

job_idstringRequired

Batch id returned when the batch was submitted.

Response

Current batch status, with clip links once finished

idstring

Batch id.

statusenum

pending is in-flight. completed means at least one clip rendered; failed means none did. Both are terminal.

Allowed values:

providerstring

Provider that voiced the batch.

modelstring

Model actually used.

audio_formatenum

Container of every clip: mp3 (128 kbps, 44.1 kHz) for ElevenLabs; wav for the rest, at 44.1 kHz for Sarvam and Smallest and 24 kHz for Vakyam.

Allowed values:

clipslist of objectsOptional

One entry per text, in submission order. Empty while pending.

audio_url_expires_ininteger or nullOptional

Seconds every audio_url in this response stays valid (900), or null when no clip rendered.

Errors

401

Unauthorized Error

404

Not Found Error

429

Too Many Requests Error