Google ships Gemini 3.8 Flash TTS: #1 pronunciation robustness, #2 voice arena at 1263 Elo
ArtificialAnlys · x · 2026-09-23
Google DeepMind released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS with preset voices and voice cloning. Per Artificial Analysis: Flash TTS debuts #2 in Provider Voice Arena at 1263 Elo (behind Sonic 3.6 at 1272) and takes #1 in pronunciation robustness at 89.5%, with three Google models in the top four. Flash-Lite hits #6 at 1236. Multilingual: Flash-Lite is #1 in Japanese, #2 Arabic, #3 German. Speed: 2.7x and 2.4x realtime. Pricing: $32.98 and $22.07 per 1M characters — pricier than Gemini 3.1 ($18.31) but far below Eleven v3 ($100).
Related event: Google Launches Gemini 3.8 Flash TTS with 30-Second Voice Cloning(27 posts)→
More from Models
- YC-backed Monte launches post-training platform to build proprietary models from your agents' real work — ycombinator · 2026-11-12
- Leak Claims OpenAI Will Launch Entire GPT-6.2 Family Tomorrow to Counter Opus 5.5 and Fable 5.2 — heypearlai · 2026-11-12
- ARC-AGI-3 leaderboard: models score 90%+ but at $10K+ per task — haider1 · 2026-11-12
- LMArena Launches Agent Arena for Head-to-Head Agent Evaluation — arena · 2026-11-12
- LLMs lack hyperlocal municipal data, explains disputed Texas power outage debate — csuwildcat · 2026-11-12
- Claude API's per-message effort lets you switch reasoning levels without breaking prompt cache — lyraxana · 2026-11-12