Supported Models
It is recommended to use speech-02-hd for the best results.
Supported Models
| Model | Description |
|---|---|
| speech-2.5-hd-preview | Latest HD model with outstanding prosody and excellent cloning similarity. |
| speech-2.5-turbo-preview | Latest Turbo model with support for 40 languages. |
| speech-02-hd | Superior rhythm and stability, with outstanding performance in replication similarity and sound quality. |
| speech-02-turbo | Superior rhythm and stability, with enhanced multilingual capabilities and excellent performance. |
| speech-01-hd | Rich Voices, Expressive Emotions, Authentic Languages. |
| speech-01-turbo | Excellent performance and low latency. |
Notes
- Using this API to generate a voice does not immediately incur a fee. The generation fee will be charged upon the first use of the generated voice in speech synthesis (excluding preview actions within this API).
- Voices generated through this API are temporary. If you wish to keep a voice permanently, you must use it in any speech synthesis API within 168 hours (7 days). Voices that are not used within this period will be automatically deleted.