Google’s new Gemini TTS models can clone a voice from 30 seconds of audio

Covered by 8 sources
Read the full article
Google launched Gemini 3.8 Flash TTS and Flash-Lite TTS models that generate customizable voices from text and can clone voices from 30-second audio samples with consent. These models support multi-language, long-form audio, and include features like voice remixing and delivery direction.

Covered by 8 sources


More in LLM & Text Generation

ChatGPT vs. Claude vs. Gemini for Data Science Work: Here’s What I Found

KDnuggets

Completely Unused ChatGPT Accounts Are Telling Users They’re in the Top Percentiles of Intelligence

Futurism