Changelog

July 9, 2026

API: list available TTS models with GET /v1/audio/models

GET /v1/audio/models returns the text-to-speech models you can pass as the model parameter, so you can populate a model picker at runtime instead of hardcoding the list.

1{
2  "models": [
3    { "id": "simba-english", "name": "Simba English", "default": true, "recommended": false, "description": "English-only synthesis; the model used when a request omits `model`.", "languages": ["en"] },
4    { "id": "simba-multilingual", "name": "Simba Multilingual", "default": false, "recommended": false, "description": "Synthesis across 30+ languages, including mixed-language input.", "languages": ["en", "fr-FR", "de-DE", "es-MX", "…"] },
5    { "id": "simba-3.0", "name": "Simba 3.0", "default": false, "recommended": false, "description": "Earlier streaming-native model, English only. Superseded by simba-3.2.", "languages": ["en"] },
6    { "id": "simba-3.2", "name": "Simba 3.2", "default": false, "recommended": true, "description": "Streaming-native model with the lowest time-to-first-byte and richest expressivity, English only today.", "languages": ["en"] }
7  ]
8}

Each entry carries the model id, a human-readable name and description, a default flag (the model used when a request omits model), a recommended flag (the model we suggest for new integrations - distinct from the default, which stays stable for backwards compatibility), and the languages it can synthesize (BCP-47 locale strings). The catalog is returned in a single response and is not paginated. These values reflect current support and can change over time, so read them at runtime rather than caching them.