AI
Google's New AI Voices Speak 100+ Languages
Google released Gemini 3.8 Flash TTS (text-to-speech) and a lighter Flash-Lite version, covering more than 100 languages and dialects with over 2,000 ready-made voices, plus the option to design a brand-new voice just by describing it in a text prompt. It can clone a voice from a 30-second sample, with consent verification built in, and watermarks everything it generates with SynthID so the audio stays traceable as AI-made. You can direct pacing, emotion and dialect line by line. It's rolling out now to Google's AI Studio, the Gemini API, Gemini Notebook and Vids, with an enterprise version "coming soon." On Hume AI's quality index, the two new models ranked #1 and #2 overall.
On your desk: worth testing alongside Suno as a cheap, multilingual voice layer for narration or dance-coaching content on Travis Wall Studio.
Read the original at Google Blog →