simba-3.0 is now the default TTS model
Requests that omit model now resolve to simba-3.0 instead of simba-english. Nothing you already send changes shape, and nothing that worked starts failing.
POST /v1/audio/speech, POST /v1/audio/stream and POST /v1/audio/stream/with-timestamps now resolve a request that omits model to simba-3.0 instead of the legacy simba-english. GET /v1/audio/models marks the change on its default flag.
Nothing you already send changes shape, and nothing that worked starts failing. A request that names a model explicitly is untouched. model: "simba-english" keeps getting Simba 1.6 English, and that model stays fully supported with nothing scheduled for removal.
What changes if you omit model:
- Non-English voices are routed to the Simba 3.0 multilingual training instead of being synthesized by the English 1.6 training
POST /v1/audio/stream/with-timestampsis supported (used to return400 speech_marks_unsupported)- Audio is Simba 3.0: streaming-native, lower time-to-first-byte
simba-3.0 was chosen over the recommended simba-3.2 precisely because it accepts everything the old default did. simba-3.2 serves a curated voice set and rejects non-English voices, so making it the default would have turned working calls into 400s.
The rendered audio does change if you omit model. Pin the old behaviour by sending model: "simba-english" explicitly if your integration depends on the Simba 1.6 output. For new English work we still recommend model: "simba-3.2".
See the docs changelog for the full detail.