Gemini 3.8 Flash-Lite TTS

Google has launched two new text-to-speech models, Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, expanding its Gemini family with tools for designing, remixing, and cloning voices. Flash TTS targets creative uses like games, audiobooks, and podcasts, while Flash-Lite TTS serves as a cheaper option for dubbing and voice agents. Both models are available now in the Gemini API and Google AI Studio. The new systems support over 100 languages, let users describe voices in plain text, and access more than 2,000 preset options. Flash TTS can clone a voice from a 30-second sample, requiring verbal consent and adding SynthID watermarks and C2PA credentials to outputs. Google reports a 71.4 score on Hume AI's Voice Design Benchmark, with partners including Figma, HeyGen, and Wondercraft integrating the models.

Google released two Gemini text-to-speech models on September 23, 2026, letting developers direct not only what a voice says but how each line is delivered, including pacing, emotion, and sounds like laughter or sighs. The launch centers on Gemini 3.8 Flash TTS for expressive voice design and Flash-Lite TTS for high-volume production such as dubbing and voice agents. Flash TTS can describe a voice in ordinary language, choose from more than 2,000 ready-made options across 100-plus languages, and build a reusable profile from a 30-second sample if the owner supplies a matching verbal consent recording. Both models support two-speaker scenes, and Google adds SynthID watermarks plus C2PA credentials on generated audio. The models are rolling out through the Gemini API and Google AI Studio, with Flash TTS in Gemini Notebook and Flash-Lite in Google Vids, while Gemini Enterprise API access and voice remixing remain pending and pricing for Lite was not disclosed.

AlphaSignal reports that Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS as its most expressive speech-generation models, available through the Gemini API and Google AI Studio's speech playground. The release follows the earlier launch of Gemini 3.8 Flash, with Flash aimed at richer performances and Technical specifics include inline tags such as [whispers], [excited], [short pause], and [slow] for mid-sentence delivery control, a director-style workflow in Google AI Studio for character Audio Profiles and scene context, two-speaker generation with per-character voice and style, and audio output as 24 kHz, 16-bit

Google has launched Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two new text-to-speech models rolling out through the Gemini API and AI Studio. The company describes them as its most expressive audio generation models yet, with the larger variant aimed at deep creative direction and the Lite version built for high-volume, cost-efficient production. Both models support over 100 languages, with a library of more than 2,000 production-ready voices, and Gemini 3.8 Flash TTS can design bespoke voices or replicate a voice from a 30-second sample using consent verification, SynthID watermarking, and C2PA credentials. Google reports a top score of 71.4 on Hume AI's Voice Design Benchmark and first-place blind preference rankings on Voice Arena in languages including Japanese, Brazilian Portuguese, and Hindi. Availability covers AI Studio, Notebook, Google Vids, and enterprise API access coming soon, while voice replication is restricted in Illinois, Texas, the EEA, UK, Switzerland, and India.

Google has introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, its most expressive audio generation models yet, expanding the Gemini Audio family with tools for creators, developers, and enterprises. The models enable users to design custom voices, replicate existing ones from short samples, and direct scenes line by line across surfaces including Google AI Studio, the Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids. Gemini 3.8 Flash TTS is built for creative direction and character design with over 100 languages and access to 2,000+ production-ready voices, while Flash-Lite targets high-volume dubbing and voice agents. On Hume AI's Voice Design Benchmark, Flash TTS took the top spot with 71.4, and both models ranked first and second on the Overall Quality Index, with Flash-Lite also leading in accent modeling at 60.8. Both are rolling out to developers via the Gemini API and AI Studio starting September 23, 2026, with enterprise API access coming soon, while flash is in Gemini Notebook and Flash-Lite in Google Vids. Safety features include a mandatory verbal consent recording for replication, SynthID audio watermarking, and C2PA credentials.