Google launches Gemini 3.8 Flash TTS, debuts #2 in blind voice arena behind Sonic 3.6
ArtificialAnlys · x · 2026-09-23
Google DeepMind released Gemini 3.8 Flash TTS and Flash-Lite TTS, supporting preset voices and voice replication. In the blind-human Provider Voice Arena, Flash TTS debuts #2 with Elo 1,263 — just 9 points behind Sonic 3.6 (1,272) and ahead of Qwen-Audio-3.0-TTS-Plus (1,260). Flash-Lite debuts #6 at 1,236, both ahead of Gemini 3.1 Flash TTS (1,199). The models also top the Pronunciation Robustness Benchmark and Japanese Controlled Voice Arena.
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