Cloned voices on simba-3.2 now enabled per workspace
Voice cloning on simba-3.2 moved from per-voice approval to per-workspace enablement. Once your workspace is enabled, every clone you own works on the model.
Luke Oliff
models
7 posts tagged "models".
- SpeechifyAI Changelog
- SpeechifyAI Changelog
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.
Luke Oliff
- SpeechifyAI Changelog
Models list now reports per-model endpoints and curated-voice flag
GET /v1/audio/models now returns endpoints and curated_voices per model, so a model picker can show only valid synthesis routes and reject unsuitable voice selections before the request reaches the server.
Luke Oliff
- SpeechifyAI Changelog
Simba 3.0 now speaks six European languages; Simba 1.6 marked legacy
Simba 3.0 is no longer English-only — it now officially covers English plus German, Spanish (ES/MX), French, Italian, and Brazilian Portuguese. The same release flags the Simba 1.6 models as legacy and confirms Simba 3.0 accepts cloned voices.
Luke Oliff
- SpeechifyAI Changelog
Cloned voices can now run on Simba 3.2 with Speechify approval
Personal cloned voices can now be synthesized on the curated Simba 3.2 model. Given the model's quality bar, each clone is gated on manual Speechify approval of the voice key, while simba-english and simba-multilingual keep serving clones self-serve.
Luke Oliff
- SpeechifyAI Changelog
List available TTS models at runtime with GET /v1/audio/models
A new GET /v1/audio/models endpoint returns the models you can pass as the model parameter, each with a default and recommended flag plus the languages it supports — so a model picker can be built at runtime instead of hardcoding the list.
Luke Oliff
- SpeechifyAI Changelog
Simba 3.2 is live on the TTS API as the recommended English model
Simba 3.2 is now available on POST /v1/audio/speech and /v1/audio/stream — a streaming-native Simba 3 model with lower TTFB, richer expressivity, and a curated voice allow-list, recommended for new English integrations.
Luke Oliff