Skip to main content
/v1/speech speaks with one of these voices. Each recording below was made through the API. Press play to hear it: nothing downloads until you do. Every voice is used with its speaker’s consent. The API does not offer voice cloning, and a voice whose consent could not be confirmed was withdrawn: a request that names it gets 400 unknown_voice, never another voice in its place.

Choosing the language

A voice speaks its first language unless you say otherwise. To make Mouhamad speak Hausa:
Asking a voice for a language it does not speak returns 400 unsupported_language, with the languages it does speak in the message.

Languages

Fulfulde and Tamasheq are part of the Lab’s research, not of the API yet. We add a language to the API when we can measure that it works.

Get the list in code

No key is needed. Read it when your app starts if you show a voice picker, so a new voice appears without an update.