Google launches Gemini 3.8 Flash TTS with 2,000+ voices, tops Hume AI benchmarks
giffmana · x · 2026-09-24
Google announced Gemini 3.8 Flash and Flash-Lite TTS, claiming new SOTA text-to-speech with a voice design experience, 2,000+ production-ready voices, voice replication, 100-language support, upcoming voice remixing, and the #1 spot on Hume AI's voice benchmarks. A reply notes hands-on voice interaction with Google Maps is still a disaster, urging the Maps team to adopt Gemini Flash TTS.
Related event: Google Launches Gemini 3.8 Flash TTS with Voice Cloning and 100+ Languages(18 posts)→
More from Multimodal
- Video diffusion models break physics because RoPE locks motion paths early, arXiv study finds — udmrzn · 2026-09-24
- Building AI video workflows with Codex driving Dreamina CLI: node-level iteration without regenerating — HeyNayeem · 2026-09-24
- Kling video API Python SDK lands on GitHub, actually calls Kling 3.0 endpoints — matchaman11 · 2026-09-24
- Seedance 2.5 holds the AI video crown as Kling 4 looms — matchaman11 · 2026-09-24
- Polyfork turns 3D assets into programs: agent-built models, revenue on day one — PeterDiamandis · 2026-09-24
- ByteDance's Dreamina launches new web experience with Canvas workflow, $1.5/month promo — alifcoder · 2026-09-24