978 ms P50 time-to-first-audio on Speko; ranked 29th of 112 in the TTS for Voice Agents 2026 index.
Benchmark summary: 26.2/100, ranked 29th of 112 in the TTS for Voice Agents 2026 index (Listed). Strongest criterion: voice quality, 17.5 of 20 points.
Google Gemini 3.1 Flash TTS is a proprietary text-to-speech (TTS) API from Google, measured by two independent benchmarks: Artificial Analysis and Speko.
Overall score
26.2 /100
Data checked on September 30, 2026
Updated after each benchmark capture
Every point comes from a public benchmark: sources · methodology
Google Gemini 3.1 Flash TTS ranks 29th of 112 in the 2026 text-to-speech (TTS) API benchmark, with a score of 26.2/100.
Speko measures a P50 TTFA of 978 ms from US East (n=30), dated July 3, 2026: 28th lowest of the 29 models Speko measures.
Speko rates its pronunciation robustness on numbers, dates and currency at 0.69 on a 0-to-1 scale (5th highest of the 28 models Speko rates).
In the Artificial Analysis Speech Arena (capture of October 1, 2026), Google Gemini 3.1 Flash TTS has an Elo of 1,205 (±12, 95% confidence) from 3,622 blind comparisons, 12th highest of the 92 models Artificial Analysis rates. Speko rates its naturalness at 1,591 Elo from blind A/B votes (6th highest of the 41 models Speko rates).
Artificial Analysis lists Google Gemini 3.1 Flash TTS at $18.3 per 1M characters (32nd lowest of the 78 models Artificial Analysis lists a price for). Speko lists a cost of about $33.3 per 1M characters.
Artificial Analysis changed its Speech Arena Elo between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (1,204, then 1,205): the score uses the average, 1,204.5. The value shown is the latest. Speko changed its pronunciation robustness between the captures of September 30, 2026 and October 1, 2026 without a new measurement date (0.68, then 0.69): the score uses the average, 0.685. The value shown is the latest.
Tested in Japanese, Chinese, Hindi, Korean, Filipino, Norwegian, Tamil, Telugu and Thai by Artificial Analysis or Speko. A language missing here was not tested, which does not mean it is unsupported.
ElevenLabs Eleven v4 is a proprietary text-to-speech (TTS) API from ElevenLabs, measured by two independent benchmarks: Artificial Analysis and Speko.
SpeechifyAI Simba 3.0 is a proprietary text-to-speech (TTS) API from Speechify, measured by two independent benchmarks: Artificial Analysis and Coval.
Murf AI Falcon 2 is a proprietary text-to-speech (TTS) API from Murf AI, measured by two independent benchmarks: Artificial Analysis and Coval.