Gemini 3.1 Flash TTS Preview

Low-latency speech generation with steerable prompts and expressive audio tags

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 DATEApr 15, 2026
WEIGHTSClosed weights
CONTEXT WINDOW8.2K
MAX OUTPUT16.4K
REASONINGNo
TOOL CALLINGNo
INPUTStext
OUTPUTSaudio

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