Google Gemini 3.8 TTS: Clone a Voice with Just a 30-Second Sample

Beating AI Newsflash: Google has released Gemini 3.8 Flash TTS and Flash-Lite TTS, two text-to-speech models now available via the Gemini API and Google AI Studio. Flash focuses on audio quality, character performance, and long-text stability, while Lite emphasizes high throughput, low latency, and cost efficiency. Both models allow users to design new voice profiles directly with text or replicate an individual's voice (with authorization) using approximately 30 seconds of reference audio. Users can control emotions, pacing, and accents sentence by sentence, and even insert sounds like laughter, sighs, and coughs. Two-person dialogues can also be generated directly from a single script. Flash supports 130 languages, while Lite supports 101. Pricing is lower than the previous generation. Until December 31, 2026, Flash audio output costs $9 per million tokens, and Lite costs $6; the previous generation Gemini 3.1 Flash TTS Preview was priced at $20. Starting January 1, 2027, the standard prices for the two models will increase to $18 and $12, respectively. [Original Link]