Gemini 3.5 Live Translate Preview

Low-latency audio-to-audio model for real-time speech translation across 70+ languages

BENCHMARKS

Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.

RELEASE DATEJun 9, 2026
WEIGHTSClosed weights
CONTEXT WINDOW131.1K
MAX OUTPUT65.5K
REASONINGNo
TOOL CALLINGNo
INPUTSaudio
OUTPUTSaudio, text

Specifications from Models.dev. Availability and limits may differ by provider. Benchmark scores come from Epoch AI under CC BY 4.0.