Simba 3.0 now supports cloned and personal voices

1 min read

simba-3.0 accepts cloned and personal voice_id values self-serve on POST /v1/audio/speech and /v1/audio/stream, the same way simba-english does; simba-3.2 cloning still requires manual approval.

Developer Relations · SpeechifyAI Labs

simba-3.0 now accepts cloned and personal voices on POST /v1/audio/speech and POST /v1/audio/stream. Pass a cloned voice’s voice_id with model: "simba-3.0", the same way you already would with simba-english. This covers zero-shot clones - built from a 10-30 second sample - which is what’s self-serve today; fine-tuned voice cloning is a separate, sales-assisted offering (contact sales).

simba-3.2 is unchanged: cloned voices are supported there too, but each one currently requires manual Speechify review and approval of the voice key before use. For self-serve cloned-voice synthesis without that approval step, use simba-3.0, simba-english, or simba-multilingual.

See the docs changelog entry for a request example.