On September 22, 2026 Google announced that the Gemini API now includes two new text‑to‑speech (TTS) models. Gemini 3.8 Flash TTS is a high‑quality, creative‑focused model with studio‑grade voice fidelity and support for many dialects. Gemini 3.8 Flash‑Lite TTS is a faster, cheaper model built for high‑throughput production and real‑time voice agents.
Why it matters
Developers can now add more natural, scalable speech output to apps, choosing between premium quality and cost‑effective real‑time voices.