Loading video...

Video Failed to Load

Go Home

Control tone, pacing, and expressive nuance. See how you can add scripted vocal bursts and backchanneling using non verbal cues like <laughs>, <sigh>, <gasp> and active-listening interjections (like |mhm| or|yeah|).

38,185 views • 14 days ago •via X (Twitter)

5 Comments

Google's profile picture
Google14 days ago

Create voices from scratch across 100+ languages and dialects using natural language prompting. Customize role, accent and voice characteristics with prompts like “subtle Southern US accent” or “soften the delivery”.

Google's profile picture
Google14 days ago

This week, we released two new audio models for creative production and cost-efficient speech at scale. Hear what's possible with Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS 🧵

Google's profile picture
Google14 days ago

Learn more about our latest Gemini audio models ↓

The Lunar Misfit's profile picture
The Lunar Misfit14 days ago

@GoogleDeepMind The first voice model that accepts <sigh> as a product requirement.

Tommy YC's profile picture
Tommy YC14 days ago

@GoogleDeepMind Prosody is the real interface.

Related Videos