Gemini 3.8 Flash TTS hands-on: voice cloning, 2000+ voices, and pricing
Sam Witteveen · youtube · 2026-09-25
- Sam Witteveen published a full hands-on video on Google's new Gemini 3.8 Flash TTS, with the official blog post and Colab notebooks.
- Covered: Flash vs Flash-Lite comparison; voice design; a 2000+ preset voice library; voice cloning with guardrails; stage directions and non-verbal tags; multi-speaker and long-form audio; benchmarks and pricing.
- Demos include AI Studio and multiple Colabs (style control, inline tags, voice design, multi-speaker dialogue, voice cloning) that viewers can run directly.
More from Multimodal
- MiniMax H3 hits 100 days open-source: 1,472 derivative models, 148M+ downloads — linoy_tsaban · 2026-11-11
- MiniMax H3-Image explodes an espresso machine photo into 15 labeled parts — Charlietest123 · 2026-11-11
- Indie dev built a tool that clips best moments from 4-hour streams in 30 minutes — kissaadams · 2026-11-11
- Non-Blender user makes a video in 30 minutes with Claude and Seedance — FinanceYF5 · 2026-11-11
- Whimsical Woodland: A Watercolor AI Art Prompt Template for Dreamy Forest Scenes — LudovicCreator · 2026-11-11
- Clean point clouds: Tersus GNSS MVP S1 scans turned into high-quality splats in LichtFeld Studio — janusch_patas · 2026-11-11