Gemini 3.5 Transcribe Live

Name: Gemini 3.5 Transcribe Live
Author: Google

Google · Released Aug 26, 2026 · Closed weights

Speech transcription model for accurate audio-to-text and captioning workflows

Price per 1M tokens: $3.5 / $21

Open in the timeline

BENCHMARKS

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

Google's past year

37 release days in the past year, about one every 10 days. The next is expected around Nov 3, 2026. Forecasts ↗

NovDecJanFebMarAprMayJunJulAugSepOctNov

Specifications

RELEASE DATEAug 26, 2026

WEIGHTSClosed weights

CONTEXT WINDOWNot listed

MAX OUTPUT0

REASONINGNot listed

TOOL CALLINGNot listed

INPUTSaudio/pcm

OUTPUTStext

Models.dev record ↗

Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.