Data read October 27, 2026
Async TTS APIs in 2026: 3 models, speed tier and languages
Async has 3 models in the database. 0 of the 3 are in the multilingual speed ranking; the others are not tagged multilingual by Coval or are not measured by it.
Every measure is copied from a public benchmark with its source on the model page; a measure no benchmark holds is shown as n/a, never estimated.
How the rows are ordered. Ranked models first, in ranking order (speed tier, then P95, ties by median); the 3 models without a rank follow alphabetically.
| Rank | Model | Speed tier From the Coval P95 | P95 (ms) 1 turn in 20 is slower | Languages tested | Listener Elo Artificial Analysis, with 95% interval | Price per 1M characters List price; a range when sources differ |
|---|---|---|---|---|---|---|
| not ranked |  async Flash v1.0 | n/a | n/a | 0 | 1,049 ±11 | $10.10 |
| not ranked |  async Flash v1.5 | n/a | n/a | 0 | 1,137 ±12 | $10.10 |
| not ranked |  async Pro v1.0 | n/a | n/a | 0 | 1,127 ±12 | $20.20 |
Frequently asked questions
- Which Async TTS model is fastest?
- No Async model is in the multilingual speed ranking.
- How many Async TTS models are covered?
- 3 models; 0 are ranked.