model

Gemini 3.5 Transcribe

Google's speech-to-text model announced Aug. 26, 2026, shipped as a sub-second streaming endpoint (gemini-3.5-transcribe-live via the Live API) and a pre-recorded endpoint (gemini-3.5-transcribe via the Interactions API), with in-model filler removal, formatting and speaker attribution.

Known aliases

3.5 Transcribe
gemini-3.5-transcribe
gemini-3.5-transcribe-live

Relationships

No evidence-backed relationships are recorded.

Current clusters

build2 distinct publishers

Google splits transcription in two, and quietly absorbs your cleanup layer

Gemini 3.5 Transcribe ships as a sub-second streaming endpoint and a batch one, with filler-word removal and formatting inside the model. The catalog and the pricing page have not caught up.

Publishers:blog.googleruntimewire.com

Reality

Evidence55
Adoption45
Hype gap+25
Incentives70