Google launches two benchmark-topping speech generation models

Google LLC released two text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, through its cloud platform on September 23, 2026. The two models share highly similar application programming interfaces, letting developers use them side-by-side, with Flash-Lite TTS optimized for cost efficiency and inference speed and Flash TTS offering better audio quality.

Google launches two benchmark-topping speech generation models SiliconANGLE https://siliconangle.com Google LLC today made two new text-to-speech https://www.machinebrief.com/glossary/text-to-speech models, Gemini https://www.machinebrief.com/glossary/gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, available through its cloud platform. The algorithms have highly similar application programming interfaces, which makes using them side-by-side relatively simple for developers. Flash-Lite TTS is optimized for cost-cost efficiency and inference https://www.machinebrief.com/glossary/inference speed. Flash TTS offers better audio quality … The post Google launches two benchmark-topping speech generation models https://siliconangle.com/2026/09/23/google-launches-two-benchmark-topping-speech-generation-models/ appeared first on SiliconANGLE https://siliconangle.com . Get AI news in your inbox Daily digest of what matters in AI. Key Terms Explained Benchmark https://www.machinebrief.com/glossary/benchmark A standardized test used to measure and compare AI model performance. Gemini https://www.machinebrief.com/glossary/gemini Google's flagship multimodal AI model family, developed by Google DeepMind. Inference https://www.machinebrief.com/glossary/inference Running a trained model to make predictions on new data. Text-to-Speech https://www.machinebrief.com/glossary/text-to-speech AI systems that convert written text into natural-sounding spoken audio.