siliconangle.com
Google launches Gemini 3.8 Flash TTS and Flash-Lite TTS with 130 languages, voice cloning, and SynthID watermarking
Tech News••
1 min read
Published by AINave Editorial • Reviewed by Ramit
TL;DRGoogle released Gemini 3.8 Flash TTS and Flash-Lite TTS, cloud-based speech models supporting up to 130 languages, 2,000+ voices, prompt-based voice cloning with consent, and SynthID watermarking. The two models share similar APIs, letting developers trade off quality for cost.
Two new TTS models with a shared API
Google launched two cloud-based text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, with nearly identical APIs to simplify side-by-side evaluation source. Flash TTS targets higher audio quality at a higher cost, while Flash-Lite TTS prioritizes inference speed and cost efficiency. Both models are
Sources
- Google launches two benchmark-topping speech generation models - SiliconANGLE
- Gemini 3.8 Flash TTS: Google's Voice Generation Models
- Google pushes voice-cloning consent onto the developer who uploads...
- Google launches two benchmark-topping speech generation...
- Google introduces new Gemini text-to-speech AI models - Overview
- Google’s new speech model Gemini 3.8 Live supports real-time reasoning
- Google launches two Gemini 3.8 models with cutting-edge reasoning capabilities
- TechNN - Google Releases Gemini 3.8 TTS Speech Models
- The-Latest - SiliconANGLE
- Google launches two benchmark-topping spe... - aVenture News
- Google launches two benchmark-topping speech generation ...
