Google DeepMind Launches Gemini 3.8 Flash and Flash-Lite Text-to-Speech Models
Google DeepMind has announced the release of two new text-to-speech (TTS) models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. These models are designed to generate speech from text, offering advanced capabilities such as voice cloning from short audio samples and performing scripts with emotional nuances, accents, and acting cues. According to Google, the models also allow for custom voice creation and control, and are intended for applications like dubbing, podcasts, and voice agents. The primary announcement came directly from Google DeepMind's blog, with various outlets reporting on the features and potential uses.
12 articles from 12 outlets covered this story. No difference in framing or figures was found between them. The underlying claim is sourced from a shipped.
What do all outlets agree on?
12 outlets covered “Google DeepMind Launches Gemini 3.8 Flash and Flash-Lite Text-to-Speech Models”. All of them report the following:
- Google DeepMind launched new text-to-speech (TTS) models
- The models are named Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS
- They offer voice cloning or replication capabilities
- They can perform scripts with emotions, accents, and acting cues
- They support custom voice creation and control
- Intended use cases include dubbing, podcasts, and voice agents
Did outlets disagree about this?
No. All 12 outlets covering “Google DeepMind Launches Gemini 3.8 Flash and Flash-Lite Text-to-Speech Models” reported it the same way — no difference in framing or figures was found between them.
Which outlets covered this?
All 12 articles found on this story, grouped by the stance of the piece. Every link goes to the original publisher.