Gemini Can Now Clone Your Voice and Perform Scripts Like an Actor
The models can create new voices from prompts, clone a voice from 30 seconds of audio and add SynthID watermarks, Google said.
- On Wednesday, Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, expanding its voice generation capabilities. Both models are rolling out immediately in the Gemini API and Google AI Studio.
- Flash TTS targets creative applications like audiobooks and podcasts, while Flash-Lite TTS offers a cost-effective option for high-volume tasks such as dubbing. Both models enable users to direct delivery line by line with stage directions.
- Leading Hume's Voice Design Benchmark with a score of 71.4, Flash TTS enables users to create voices from plain language prompts in more than 100 languages or clone voices using audio samples.
- Initial partners integrating the models include Figma, HeyGen, Wondercraft, Linguana and Ollang. Every generated clip carries a SynthID watermark, while replicated voices include C2PA content credentials for transparency.
- As Google enters a market featuring specialists like ElevenLabs and India's Murf, upcoming features include voice remixing and enterprise access. Flash TTS will expand to Gemini Notebook, and Flash-Lite TTS will integrate with Google Vids.
20 Articles
20 Articles
Gemini can now clone your voice and perform scripts like an actor
TL;DR Google is rolling out Gemini 3.8 Flash TTS and Flash-Lite TTS, its latest text-to-speech models for more expressive AI-generated audio. Gemini 3.8 Flash TTS can create custom voices, replicate an authorized voice from a 30-second sample, and control accents, pacing, emotion, and two-speaker dialogue. The new models are reaching Gemini Notebook and Google Vids, with both also available to developers through Google AI Studio and the Gemini …
Gemini 3.8 Flash TTS, Gemini 3.8 Flash-Lite TTS Introduced by Google With Custom Voice Design and SynthID Watermarking | 📲 LatestLY
Google has launched Gemini 3.8 Flash TTS and Flash-Lite TTS models, introducing custom voice design, line-by-line performance direction, and voice replication from 30-second samples. Backed by SynthID watermarking and strict consent verification, the models are now available in Google AI Studio and the Gemini API. 📲 Gemini 3.8 Flash TTS, Gemini 3.8 Flash-Lite TTS Introduced by Google With Custom Voice Design and SynthID Watermarking.
Gemini 3.8 TTS can design voices from prompts and clone them
“Today, we’re introducing two new text-to-speech models to the Gemini family, transforming voice generation from static presets into a dynamic creative studio,” Google wrote in its announcement. Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS on Wednesday. Both are rolling out from today in the Gemini API and Google AI Studio. They […] This story continues at The Next Web
Google launches Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two models of AI dedicated to voice synthesis. To design custom voices or clone existing vocal profiles with precision.
These tools enable the creation of realistic sounds with a text command and control the tone of dialogues in more than 100 languages. The post Google unveils Gemini 3.8 audio models for professional text-to-audio conversion [watch] appeared first on Digitato.
Coverage Details
Bias Distribution
- 50% of the sources lean Right
Factuality
To view factuality data please Upgrade to Premium
