{"slug": "google-launches-two-benchmark-topping-speech-generation-models", "title": "Google launches two benchmark-topping speech generation models", "summary": "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.", "body_md": "# Google launches two benchmark-topping speech generation models\n\n[SiliconANGLE](https://siliconangle.com)\n\nGoogle 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 […]\n\nThe 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).\n\nGet AI news in your inbox\n\nDaily digest of what matters in AI.\n\n## Key Terms Explained\n\n[Benchmark](https://www.machinebrief.com/glossary/benchmark)\n\nA standardized test used to measure and compare AI model performance.\n\n[Gemini](https://www.machinebrief.com/glossary/gemini)\n\nGoogle's flagship multimodal AI model family, developed by Google DeepMind.\n\n[Inference](https://www.machinebrief.com/glossary/inference)\n\nRunning a trained model to make predictions on new data.\n\n[Text-to-Speech](https://www.machinebrief.com/glossary/text-to-speech)\n\nAI systems that convert written text into natural-sounding spoken audio.", "url": "https://wpnews.pro/news/google-launches-two-benchmark-topping-speech-generation-models", "canonical_source": "https://www.machinebrief.com/news/google-launches-two-benchmark-topping-speech-generation-mode-qgkq", "published_at": "2026-09-24 00:22:07+00:00", "updated_at": "2026-09-24 01:26:00.720842+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "ai-products", "natural-language-processing", "ai-tools"], "entities": ["Google LLC", "Gemini 3.8 Flash TTS", "Gemini 3.8 Flash-Lite TTS", "Google Cloud", "Google DeepMind"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/google-launches-two-benchmark-topping-speech-generation-models", "markdown": "https://wpnews.pro/news/google-launches-two-benchmark-topping-speech-generation-models.md", "text": "https://wpnews.pro/news/google-launches-two-benchmark-topping-speech-generation-models.txt", "jsonld": "https://wpnews.pro/news/google-launches-two-benchmark-topping-speech-generation-models.jsonld"}}