Audio

List Speech Voices

List the voices accepted by the text-to-speech models, with language and gender.

Send a listed id (or its name) as voice to POST /v3/audio/speech. Each voice carries the provider/model identifiers that accept it.

get/v3/audio/voices

Request

modelstring nullable

Restrict to one model, e.g. 'openai/tts-1'. Accepts a model id or any of its active aliases. Default: every speech model available to you.

languagestring nullable

Keep voices speaking this language. A bare code ('fr') matches every region; 'fr-CA' matches that locale only. Multilingual voices are always kept.

gender'male' | 'female' | 'unknown' nullable

Keep voices of this gender.

Successful Response

object'list'

Object type

No recorded changes to this operation across all 1 revision of this API.