Google's Gemini 3.8 Flash TTS Claims Top Voice AI Benchmark at 89.5%
As seen on the 24/7 Wall St. homepage on September 23, 2026.
Google now holds three of the top four slots on this voice benchmark, pushing xAI's TTS down to third as enterprise voice-AI contracts get decided on exactly these scores.
Gemini 3.8 Flash TTS takes the #1 spot on the Artificial Analysis Pronunciation Robustness benchmark at 89.5%, ahead of Gemini 3.1 Flash TTS at 88.2%, SpaceXAI TTS at 87.6%, and Gemini 3.8 Flash-Lite TTS at 87.4%. Gemini 3.8 Flash TTS leads on Contextually Appropriate https://t.co/6d0KJ2rlHW
- Replies2
- Reposts0
- Likes9
Continue ReadingShow less
Gemini 3.8 Flash TTS scored 89.5% on the Artificial Analysis Pronunciation Robustness benchmark, placing it first among all text-to-speech models currently tracked on the leaderboard. The result extends Google's lead in a corner of AI that enterprise customers are paying close attention to as they lock in voice-AI contracts.
The gap between first and fourth place is narrow, and Google occupies three of the top four positions, with xAI holding the only non-Google slot in that group.
Sponsored
Twelve Tabs, One Thesis
Your Research Resets Every Morning
The quote page in one tab. Filings in another. A chart you rebuilt from scratch, a transcript you never went back and found, a screener whose settings you will redo next week. Nothing you built yesterday is still there.
AlphaSpace replaces all of it with one screen you arrange yourself. Earnings calendar, estimate versus actual, the call transcript, live news, your own charts, every panel wired to whatever ticker you click. Close the browser and it is all still sitting there tomorrow.
See What a Built View Looks Like →
(Sponsor)
That concentration matters for investors in Alphabet. When a vendor holds three of the four top scores on the benchmark buyers use to evaluate bids, competing on price becomes harder for challengers and switching costs rise for customers already on Google's stack.
The second metric in the benchmark post, Contextually Appropriate, was cut off in the source, so the Pronunciation Robustness finish is the only confirmed first-place result in the evaluation suite.
Mentioned: GOOGL