Skip to main content
Audio modelActive

Gemini 3.8 Live

Google

Released
-
Data date
September 22, 2026
Access

Profile

Specifications and access

Published information about this model. Existing estimates are explicitly labeled.

SpecificationValue and source
Model class
Real-time audio modelSource
Access
API model ID
gemini-3.8-liveSource
Input
Text, image, audio and videoSource
Output
Text and audioSource
Task
Voice agents and dialogueSource
Supported details
Low latency without reasoning delaySource
Input limit
131,072 tokensSource
Output limit
65,536 tokensSource
Tools
Function calling and search groundingSource