DeepMind Unveils Gemini 3.8 TTS with Voice Cloning and Multi-Speaker Dialogue

Google DeepMind launched Gemini 3.8 Flash and Flash-Lite TTS, its most expressive text-to-speech models yet, supporting multi-speaker dialogue with interruptions, prompt-designed voices, and voice cloning.

2026-09-24 ~ 2026-09-25 · 3 related posts

Full story(4 episodes)→