SpaceXAI Grok TTS xAI · text-to-speech (TTS) API

Speed

On Coval's 30-day window ending October 22, 2026 (3,371 runs from US East), SpaceXAI Grok TTS starts speaking after 358.4 ms on a typical turn (median) and 489 ms on a slow turn (P95, the slowest one in twenty). That P95 is 22nd lowest of the 32 models Coval measures, which puts it in the Visible delay tier: the voice becomes a visible part of the delay. On the median it is a tie (gap under 10 ms) with Smallest.ai Lightning V3.1 Pro (Jul 2026). Speko's board plots it at 258 ms time to first audio from US East; its model page reports a 272 ms sweep.

Voice quality

Speko rates its naturalness at 1,495 Elo from blind A/B votes on phone-agent lines (25th highest of the 43 models Speko rates). In the Artificial Analysis Speech Arena it holds 1,150 ±13 Elo (95% interval), 29th highest of the 98 models Artificial Analysis rates; scores whose intervals overlap are a tie. In its Customer Service category, Artificial Analysis places it 25th, at 1,188 Elo.

Numbers and dates

Speko's pronunciation test on numbers, dates and currency scores it 0.45 on a 0-to-1 scale (10th highest of the 30 models Speko scores). This is the accuracy measure used here; Coval's word error rate separates models too little to compare them.

Price

Coval lists $15 per 1M characters (since Aug 10, 2026). Artificial Analysis lists $15. Speko lists about $15. List prices, as each source prints them.

Languages tested

Tested in Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi, Vietnamese, Filipino and Thai by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.