Google Debuts Two Top-Ranked Text-to-Speech Models

Google has launched Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two new text-to-speech models available via its cloud platform. Flash TTS supports 130 languages and prioritizes audio quality, while Flash-Lite TTS covers 101 languages and is optimized for speed and cost. Both offer access to over 2,000 preset voices and allow custom voice creation via text prompts or 30-second audio samples. The models topped Hume AI's audio quality benchmark and outperformed competitors on multiple language-specific Voice Arena tests. Google embeds inaudible SynthID watermarks and C2PA records in all generated audio to support transparency and detection of AI-produced content.