Skip to main content
Audio modelActive

Gemini 3.5 Transcribe

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
Speech recognitionSource
Access
API model ID
gemini-3.5-transcribeSource
Input
AudioSource
Output
TextSource
Task
TranscriptionSource
Supported details
Language detection, diarization, and timestampsSource
Languages
Over 85; code-switching within an audio fileSource
Audio duration
Up to 1 hour; up to 30 minutes with diarization or word timestampsSource
Speaker diarization
Up to 8 speakers; experimental for 3 or moreSource