xAI · Proprietary · Read 2026-10-27
SpaceXAI Grok TTS: latency, voice quality, price and languages
- Rank
- 18 / 23
- Speed tier
- Visible delay
- P95
- 473.9 ms
- Price / 1M chars
- $15
SpaceXAI Grok TTS is a proprietary text-to-speech model from xAI. Coval measures a median of 329.8 ms and a P95 of 473.9 ms to first audio, which puts it in the Visible delay speed tier, rank 18 of 23 in the multilingual ranking. Artificial Analysis or Speko tested it in 11 languages.
This summary is generated from the measures below; it is not a vendor description. Measures a source does not hold are shown as n/a and are never estimated.
Speed (Coval, 30 days, US East, English)
| Speed tier | Visible delay |
| Median time to first audio | 329.8 ms |
| P90 | 427.3 ms |
| P95 | 473.9 ms |
| Mean | 345.9 ms |
| Standard deviation | 155.4 ms |
| Calls in the window | 2,803 |
| Cekura median, streamed text | 157 ms |
| Cekura median, full text | 358 ms |
Voice quality (never added together)
| Listener Elo (Artificial Analysis) | 1,155 ±13 |
| Customer-service Elo (Artificial Analysis) | 1,193 ±27 |
| Naturalness (Speko) | 1,495 |
| Naturalness estimate (Cekura, 1 to 5) | 4.17 |
Accuracy
| Reading accuracy (Cekura) | 87.4% |
| Numbers (Cekura) | 82% |
| Codes (Cekura) | 86% |
| Context (Cekura) | 100% |
| Medical terms (Cekura) | 99% |
| Hard passages judged correct (Artificial Analysis) | 87.6% |
| Numbers and dates (Speko score) | 0.45 |
| Word error rate (Coval) | 1.7% |
Price per 1 million characters
| Range across sources | $15 |
| Artificial Analysis | $15 |
| Speko | $15 |
| Coval | $15 |
| Cekura | $15 |
Coverage
| Access | Proprietary |
| Streaming | Measured |
| Coval tags | emotion-control, multilingual, voice-cloning |
| Rated for | Knowledge sharing, Assistants, Entertainment, Customer service |
| Languages tested | Arabic, Chinese, Filipino, French, German, Hindi, Japanese, Portuguese, Spanish, Thai, Vietnamese |
Not collected
Every measure of the database is filled for this model.
Sources
- https://artificialanalysis.ai/text-to-speech (read 2026-10-27)
- https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice (read 2026-10-27)
- https://benchmarks.cekura.ai/text-to-speech (read 2026-10-27)
- https://benchmarks-api-6wxgp27p2a-ue.a.run.app/v1/results/aggregates?benchmark=TTS&window=30d&include_series=false (read 2026-10-27)
- https://benchmarks.speko.ai/tts/ (read 2026-10-27)
- Vendor site: https://docs.x.ai/overview
Keep exploring
Frequently asked questions
- How fast is SpaceXAI Grok TTS?
- Coval measures a median time to first audio of 329.8 ms and a P95 of 473.9 ms for SpaceXAI Grok TTS, over 30 days from the US East in English (Visible delay tier).
- How much does SpaceXAI Grok TTS cost?
- The benchmarks print a list price of $15 per million characters for SpaceXAI Grok TTS.
- Which languages was SpaceXAI Grok TTS tested in?
- Artificial Analysis or Speko tested SpaceXAI Grok TTS in Arabic, Chinese, Filipino, French, German, Hindi, Japanese, Portuguese, Spanish, Thai, Vietnamese.