497 ms P50 time-to-first-audio on Speko; ranked 25th of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 29.4/100, ranked 25th of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 18.6 of 20 points.
Google Gemini 3.8 Flash-Lite TTS is a proprietary text-to-speech (TTS) API from Google, measured by two independent benchmarks: Artificial Analysis and Speko.
Overall score
29.4 /100
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Google Gemini 3.8 Flash-Lite TTS ranks 25th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 29.4/100.
Speko measures a P50 TTFA of 497 ms from US East (n=30), dated September 24, 2026: 25th lowest of the 29 models Speko measures.
Speko rates its pronunciation robustness on numbers, dates and currency at 0.73 on a 0-to-1 scale (3rd highest of the 28 models Speko rates).
In the Artificial Analysis Speech Arena (capture of October 1, 2026), Google Gemini 3.8 Flash-Lite TTS has an Elo of 1,240 (±15, 95% confidence) from 2,294 blind comparisons, 6th highest of the 92 models Artificial Analysis rates. Speko rates its naturalness at 1,639 Elo from blind A/B votes (4th highest of the 41 models Speko rates).
Artificial Analysis lists Google Gemini 3.8 Flash-Lite TTS at $11 per 1M characters (15th lowest of the 78 models Artificial Analysis lists a price for). Speko lists a cost of about $10 per 1M characters.
Speko changed its pronunciation robustness between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (0.68, then 0.73): the score uses the average, 0.705. The value shown is the latest.
Tested in Spanish, German, French, Portuguese, Japanese, Chinese, Arabic, Hindi and Vietnamese by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.
Google Gemini 3.8 Flash TTS is a proprietary text-to-speech (TTS) API from Google, measured by two independent benchmarks: Artificial Analysis and Speko.
Fish Audio OpenAudio S1 is a proprietary text-to-speech (TTS) API from Fish Audio, measured by two independent benchmarks: Artificial Analysis and Coval.
Fish Audio S2.1 Pro is a proprietary text-to-speech (TTS) API from Fish Audio, measured by three independent benchmarks: Artificial Analysis, Coval and Speko.