whatmodel.sh / tts / Grok TTS
Grok TTS
↗ share
+ contribute
Grok TTS is a closed-weights text-to-speech model from xAI, released April 2026. Licence: proprietary.
Catalogue identity notes
Vapi registry xai-xai-tts, apiModelId xai-tts (REST); registry notes the vendor console id is unverified and mirrors the arena id. The WebSocket 'Grok TTS (Streaming)' entry is the same stack and is not imported. Rating-only comparison identity; no price, API or run metadata asserted.
Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.
$ how it compares
The text-to-speech models ranked either side of Grok TTS, out of 148 with a score.
| # | model | score | where |
|---|---|---|---|
| 9 |  dots.tts MF 2B (MeanFlow, NFE 4) | 68±3 | local |
| 10 |  Raon-OpenTTS-1B | 68±2 | comparison only |
| 11 | Grok TTS | 68±3 | api $15.00/M chars |
| 12 |  FireRedTTS3 (base) | 67±3 | local |
| 13 |  Simba 3.2 | 67±3 | api $6.00/M chars |
see all text-to-speech models · find the ones that fit your machine
$ what it's good at
other tests3 not in a task · 97% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot | 1271.0 ✎ | ▁···▁▃··█▄▁▇ beats 16/18 | 61% |
| Vapi Humanness · historical Elo, 2026-06-10 | 1306.5 ✎ | ▃·▃▃▃·▃██▃·▃ beats 12/12 | 32% |
| Arabic TTS Arena · community blind A/B rating, 2026-09-24 snapshot | 1063.4 ✎ | ▂▂··▃·█▅···▂ beats 9/12 | 4.3% |
$ where to run it
Through an API
api · $15.00/M chars · docs.x.ai ↗ · price sourceUSD per 1M input characters: xAI Voice Pricing lists Text to Speech at $15.00 / 1M chars. The xAI TTS REST endpoint (POST /v1/tts) takes no model parameter, so this single published rate covers it. Product: xAI Text to Speech API. API model: xAI TTS (REST /v1/tts, no model id). Settings: REST. Price basis: published list rate. Currency: USD. xAI official models/pricing docs, observed 2026-09-25.
$ how the score was worked out · The Humanness Index by Vapi ·… 61%, The Humanness Index by Vapi ·… 32%, Arabic TTS Arena (Navid AI) ·… 4%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 The Humanness Index by Vapi · September 2026 public standings | 1 | 61% |
| The Humanness Index by Vapi · June 2026 production export | 1 | 32% |
| Arabic TTS Arena (Navid AI) · leaderboard snapshot 2026-09-24 | 1 | 4% |
| prior · pull toward the middle | 3% | |
| weighted average | = 67.6 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json