xAI · read on October 27, 2026
SpaceXAI Grok TTS
SpaceXAI Grok TTS is a TTS (text-to-speech) model from xAI. Coval measures its P95 time to first audio at 473.9 ms, which puts it in the Visible delay speed tier. It ranks 23 of 86 in the full ranking.
- Speed tier
- Visible delay
- P95 / median
- 473.9 ms / 329.8 ms
- Listener Elo
- 1,155
- Price per 1M chars
- $15
Where it ranks
Full ranking: 23 of 86. Use case ranks, by speed:
The tier and the ranks are computed by this site from the benchmarks' figures, not declared by xAI.
Measurements and sources
Coval
| Median time to first audio (P50) | 329.8 ms |
| Time to first audio, P95 | 473.9 ms |
| Time to first audio, mean | 345.9 ms |
| Time to first audio, P90 | 427.3 ms |
| Timed requests | 2,803 |
Speko
| Naturalness score | 1,495 |
| Latency, board chart | 258 ms |
| Latency, model page sweep (median) | 272 ms |
| Numbers and dates pronunciation | 0.45 |
Artificial Analysis
| Listener Elo | 1,155 |
| Listener Elo, 95% interval | 13 |
| Listener Elo, customer service | 1,193 |
| Hard passages pronounced correctly | 87.6% |
Cekura
| Time to first audio, streamed text | 157 ms |
| Time to first audio, text sent whole | 358 ms |
| Reading accuracy | 87.4% |
| Estimated naturalness (1 to 5) | 4.17 |
Details
| Provider | xAI |
| Access | Proprietary |
| Streaming | A benchmark measures its time to first audio |
| Features listed by Coval | emotion-control, multilingual, voice-cloning |
| Languages tested | Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi, Vietnamese, Filipino, Thai |
| Measured by | Artificial Analysis, Cekura, Coval, Speko |
| Official site | docs.x.ai/overview |
Sources
- https://artificialanalysis.ai/text-to-speech (read on October 27, 2026)
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (read on October 27, 2026)
- https://benchmarks.cekura.ai/text-to-speech (read on October 27, 2026)
- https://benchmarks-api-6wxgp27p2a-ue.a.run.app/v1/results/aggregates?benchmark=TTS&window=30d&include_series=false (read on October 27, 2026)
- https://benchmarks.speko.ai/tts/ (read on October 27, 2026)
Values are copied from these pages on the date shown. The match between this model and its benchmark entries is inferred, because a source writes the name differently: Cekura: “Grok TTS”; Coval: “SpaceXAI Grok TTS”; Speko: “xAI Grok grok-tts”. See the methodology.
Compare it with the reference model: Gradium TTS vs SpaceXAI Grok TTS.