Gemini 3.8 text-to-speech
Gemini 3.8 text-to-speech says hello, and it's a big deal. Google just launched two new AI models that can create and customize realistic voices from scratch. You can direct these voices to sound exactly how you want, from their accent to their emotional tone.
The new models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, can generate high-quality audio for audiobooks, podcasts, and real-time voice agents. They also come with built-in safety tools like watermarking to keep your generated audio secure.
These models are a game-changer for creators, developers, and enterprises. They can build high-quality, multilingual voice experiences worldwide, and are already being used by companies like Figma and HeyGen to accelerate global dubbing and localization.
Story 1 of 10