Audio modelActive
Aura-2
Deepgram
- Released
- -
- Data date
- September 22, 2026
- Model class
- Access
Aura-2 is Deepgram’s multilingual text-to-speech family, with voices for English, Spanish, German, French, Dutch, Italian, and Japanese. The model ID used here is aura-2-thalia-en through the /v1/speak endpoint.
With Aura-2, the model identifier also selects a concrete voice. aura-2-thalia-en is the English Thalia variant; German or Japanese output requires another voice identifier. Deepgram also positions Aura-2 for languages that its English-focused Flux TTS does not cover.
Specifications and access
| Specification | Value and source |
|---|---|
| Model class | Text-to-speechSource |
| Access | APISource |
| API model ID | aura-2-thalia-enSource |
| Input | TextSource |
| Output | AudioSource |
| Task | Speech generationSource |
| Supported details | The API documentation shows the aura-2-thalia-en voiceSource |
| Languages | Voices for English, Spanish, German, French, Dutch, Italian and JapaneseSource |
| API endpoint | /v1/speak; the model ID selects a specific voiceSource |
Popularity
43.6 / 100
Sources and data date
| Type | Evidence and data date |
|---|---|
| Additional source | Deepgram text-to-speech documentation (retrieved September 22, 2026) · Deepgram text-to-speech models and languages · Editorial description reviewed October 2, 2026 |
| Additional source | OpenRouter: Popularity index (derived), CC BY 4.0 |
| Additional source | Vercel AI Gateway: Popularity index (derived), CC BY 4.0 |
| Additional source | Creative Commons Attribution 4.0 |