Data read October 27, 2026
Headroom TTS APIs in 2026: 4 models with a P95 under 120 ms
4 models fall in the Headroom tier: a P95 under 120 ms on Coval's 30-day measure from the US East. The first is Gradium TTS.
Tiers are drawn at the widest gaps between consecutive P95 values, so they do not depend on any one model. A model Coval does not measure has no tier.
How the rows are ordered. Ranked models first, in ranking order (speed tier, then P95, ties by median); the 1 models without a rank follow alphabetically.
| Rank | Model | Median (ms) Typical wait before the first sound | 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 |
|---|---|---|---|---|---|---|
| 1 = |  Gradium TTS | 53.7 | 104.3 | 4 | 1,174 ±13 | $36 to $57.80 |
| 1 = |  Inworld Realtime TTS-2 Flash | 58.1 | 100.9 | 9 | 1,218 ±13 | $10.40 to $15 |
| 1 = |  Alibaba Qwen3 TTS Fast | 62.9 | 98.8 | 0 | n/a | $10 |
| not ranked | | 39.7 | 75.0 | 0 | n/a | $9 |
Frequently asked questions
- What does the Headroom speed tier mean?
- A TTS model is in the Headroom tier when it has a P95 under 120 ms. P95 is the slow turn: one call in twenty is slower.
- Which TTS APIs are in the Headroom tier?
- Starting with the best-ranked, Gradium TTS, Inworld Realtime TTS-2 Flash, Alibaba Qwen3 TTS Fast, and Fluxions vui. There are 4 in total.