Google launches Gemini 3.8 Flash TTS models
Original: Gemini 3.8 text-to-speech
Why This Matters
Natural-language voice creation lowers the barrier to professional audio production significantly.
Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS on September 23, 2026, describing them as its most expressive audio generation models to date. Both models are available across Google AI Studio, Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids.
Google has introduced two new text-to-speech models: Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. The company bills them as its most expressive audio generation models yet. Users can create custom voices from scratch or replicate existing ones using natural language prompts — no audio samples required. The models also support line-by-line dialogue direction, giving creators control over pacing, emotion, and conversational sounds. Deployment spans Google AI Studio, the Gemini API, Gemini Enterprise, Gemini Notebook, and Google Vids. The announcement was authored by Leland Rechis (Group Product Manager) and Alan Cowen (Director, Research Science), on behalf of the Gemini Audio Team. The Lite variant suggests Google is targeting cost- and latency-sensitive use cases alongside the full Flash model.