Marking our third audio model release in < 30 days, today we're introducing two new text-to-speech models from @GoogleDeepMind: ๐Ÿ”‰ Gemini 3.8 Flash TTS: Built for deep creative direction and character design. Design entirely new voices from scratch using natural language prompts across 100+ languages and dialects. ๐Ÿ”Š Gemini 3.8 Flash-Lite TTS: Built for high-volume, cost-efficient scale. Optimized for high-volume dubbing, audio content creation, and expressive voice agents with fine-grained control over tone, pacing, and expressive nuance.

Sep 23, 2026 ยท 3:29 PM UTC

5
2
45
5,839
To help protect creators and keep AI speech transparent, every AI-generated audio clip includes imperceptible SynthID watermarking. These new Gemini Audio models are rolling out today across @GoogleAIStudio, @Gemini_Notebook, and the Gemini API. Coming soon to Google Vids and Gemini Enterprise. Learn more โ†“ goo.gle/3V5NpRb

Gemini 3.8 text-to-speech says hello

Gemini 3.8 Flash-Lite TTS and Gemini 3.8 Flash TTS are our most expressive audio models yet.

blog.google
2
864
Sort replies: Relevant Recent Liked
Replying to @NewsFromGoogle @GoogleDeepMind
Congratulations to everyone involved in bringing Gemini 3.8 Flash TTS! You all have done something amazing. I hope each of you have an incredible week you all deserve it!
1
17
Replying to @NewsFromGoogle @GoogleDeepMind
ASSIST me to pass this letter to @googlecloud
15