ModelsSep 24, 2026 · 00:174 sources

Google Gemini 3.8 Flash TTS Takes #1 in Pronunciation Robustness

From marketbrief.now

Image: marketbrief.now
AI;DR

Google DeepMind released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two text-to-speech models with voice replication and support for 100 languages. The Flash TTS model scored 89.5% on the Pronunciation Robustness Benchmark, taking the top spot from Gemini 3.1 Flash TTS, and debuted at #2 on the Provider Voice Arena Leaderboard with an Elo of 1,263, while Flash-Lite ranked #6 with 1,236. The models are available via the Gemini API and AI Studio with over 2,000 voices, priced at $32.98 and $22.07 per 1 million characters respectively, both higher than the $18.31 rate for Gemini 3.1 Flash TTS but below Eleven v3 at $100 per 1 million characters.

Read the sourceSign in to suggest

Sources

#google#gemini#text-to-speech#multimodal#deepmind#anthropic#claude#multi-agentMarkdown
Content history (2)
  • 2026-10-04 · Summary · vi · Replaced stored text
    Google DeepMind vừa ra mắt hai mô hình text-to-speech là Gemini 3.8 Flash TTS và Gemini 3…
    Google DeepMind vừa phát hành Gemini 3.8 Flash TTS và Gemini 3.8 Flash-Lite TTS, hai mô h…
  • 2026-10-04 · Title · vi · Replaced stored text
    Google Gemini 3.8 Flash TTS dẫn đầu về độ bền phát âm
    Google Gemini 3.8 Flash TTS giành vị trí số 1 về độ vững vàng phát âm

One ranked edition, every morning

The stories that matter today. Free, cancel anytime.

Telegram @aidr_today