Changelog

simba-3.0 is no longer English-only. It now officially supports English plus German, Spanish (Spain and Mexico), French, Italian and Brazilian Portuguese:

Nothing changes in your request shape. Keep passing model: "simba-3.0" and set the language parameter to the language of your input; when you omit language, the voice’s own locale decides. English and non-English are served by two separate trainings behind the scenes, but that routing is internal, so the model ID you pass never changes.

$
curl -X POST https://api.speechify.ai/v1/audio/speech \
>
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "input": "Bonjour, comment allez-vous ?",
>
    "voice_id": "oliver",
>
    "model": "simba-3.0",
>
    "language": "fr-FR"
>
  }'

A non-English voice on simba-3.0 previously returned 400; those requests now synthesize. Languages outside the supported set often produce usable audio but are not validated - use simba-multilingual for the full 30+ locale set. simba-3.2 remains English-only and stays the recommendation for English integrations.

GET /v1/audio/models reports the new coverage in simba-3.0’s languages array, so a picker driven by that endpoint picks it up with no code change.

Simba 1.6 models marked legacy

GET /v1/audio/models carries a new deprecated boolean, set on simba-english and simba-multilingual:

1
{
2
  "id": "simba-english",
3
  "name": "Simba English",
4
  "default": true,
5
  "recommended": false,
6
  "deprecated": true,
7
  "description": "Legacy Simba 1.6 English model, still the default when a request omits `model`. Prefer simba-3.2.",
8
  "languages": ["en"]
9
}

The flag is advisory. Both models stay fully supported and behave exactly as before, and nothing is scheduled for removal - simba-english is still the model a request resolves to when it omits model, so it cannot be withdrawn. Treat deprecated as a signal to de-emphasise a model in a picker and steer new integrations elsewhere: simba-3.2 for English, simba-3.0 for the languages it covers.

simba-3.0 accepts cloned voices

The docs previously said Simba 3.0 served a curated voice set and rejected cloned/personal voices. That was not what the API did: simba-3.0 accepts the full built-in catalog and any cloned voice, self-serve. The documentation now matches the behavior.

simba-3.2 is unchanged and remains the one model with a curated voice set, plus cloned voices Speechify has manually approved.

Playground language picker

The Console TTS playground now has a language selector next to the model picker. Choosing a multilingual model lets you set the language parameter directly, and the sample text follows your choice so you have something in that language to synthesize.