Overview
The fast, cost-efficient text-to-speech model in Gemini 3.8 for high-throughput production and real-time voice-agent cascades.
Gemini 3.8 Flash-Lite TTS
The fast, cost-efficient text-to-speech model in Gemini 3.8 for high-throughput production and real-time voice-agent cascades.
Google announced Gemini 3.8 Flash-Lite TTS GA in the Gemini API on 2026-09-22; model ID `gemini-3.8-flash-lite-tts`, targeting high-throughput, low-latency production TTS and replacing `gemini-3.1-flash-tts-preview`.
MODEL NUMBER087
- First public date
- 2026-09-22
- Organization
- Google DeepMind
- Family
- Gemini
01
Specifications
Only published specifications are shown.
02
Overview
Why it mattered
It moves the TTS preview line into a stable release and provides a lower-latency production tier for high-throughput voice workflows.
03
Architecture & capabilities
Model capabilities
Audio generationVoice cloningMultilingual
04
Release history
Gemini 3.8 Flash-Lite TTS reached GA in the Gemini API for high-throughput, low-latency production TTS, replacing Gemini 3.1 Flash TTS Preview.
View source05
Related models
Select a card to view the related model.
06
Sources
Suggest a correction
Copy this template, add the field, proposed value, and primary source, and share it with the archive maintainer.