Google Introduces Advanced Text-to-Speech Models for Custom Voice Creation

Sep 23, 2026

AI Summary

Google has launched Gemini 3.8 Flash TTS and Flash-Lite TTS, new text-to-speech models that allow users to create and customize realistic voices for various applications. These models enhance audio generation capabilities, support over 100 languages, and include safety features to ensure responsible use.

Gemini 3.8 Flash TTS and Flash-Lite TTS are new audio generation models from Google, enabling users to create custom character voices and direct scene dialogue.
The models provide enhanced expressiveness and control over voice delivery, making them suitable for audiobooks, games, and podcasts.
They support over 100 languages and have received high rankings in voice customization and overall quality benchmarks.
New safety features include consent verification for voice replication and audio watermarking to prevent misinformation.
Developers can access these capabilities through Google AI Studio and the Gemini API, with partnerships established for integration into various platforms.
The models are designed to improve user experiences in products like Gemini Notebook and Google Vids, and they are rolling out starting today.

text-to-speechgeminiai modelsspeech synthesisinnovation

Google Introduces Advanced Text-to-Speech Models for Custom Voice Creation

Related Stories

Synthesia Creates Interactive Digital Avatars for Personalized Communication

Meta's Muse AI outperforms ChatGPT as OpenAI and Anthropic release new models

AI Chatbots Gain Popularity as Sources of Emotional Support and Guidance

Development of Mini-AGI Model Focuses on Dynamic Learning with Limited VRAM