🤖 Google drops two top-tier speech AI models
Google has released two new benchmark-topping text-to-speech models: Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. These models are available via Google's cloud platform, offering different trade-offs between cost efficiency and audio quality. As of the launch, Flash TTS supports 130 languages, whereas Flash-Lite TTS supports 101 languages. Developers can customize voices using prompts or from 30-second samples, with consent required for replication. Google has implemented SynthID watermarking and C2PA records for enhanced transparency. 🤖