Provider · read on October 27, 2026
Async text-to-speech models, ranked by speed
3 of the 96 text-to-speech (TTS) models in this index are filed under Async , led by async Flash v1.5, async Pro v1.0 and async Flash v1.0. Same order and same measures as the full ranking.
| Rank | Model | Speed tier | P95 | Speed (shorter is faster) | Median | Listener Elo | Price per 1M chars | Best for |
|---|---|---|---|---|---|---|---|---|
| 44 (tie) |  async Flash v1.5Async | No tier | Not timed | Not timed | Not timed | 1,137 | $10.1 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 45 |  async Pro v1.0Async | No tier | Not timed | Not timed | Not timed | 1,127 | $20.2 | Customer service, Assistants, Entertainment, Knowledge sharing |
| 63 (tie) |  async Flash v1.0Async | No tier | Not timed | Not timed | Not timed | 1,049 | $10.1 | Customer service, Assistants, Entertainment, Knowledge sharing |
Frequently asked questions
- Which Async TTS model is the fastest?
- None of the 3 models on this page is timed by Coval, so no speed comparison is made. They are ordered by listener Elo from Artificial Analysis where it is published.
- How are these models ordered?
- As in the full ranking: speed tier, then P95 time to first audio, with ties within 10 ms ordered by median time to first audio. Models Coval does not time follow, ordered by listener Elo; models with neither measure come last, in alphabetical order.