Not established from the available sources.
GOOGLE DEEPMIND · MODEL RELEASE TRACKER
Gemini 3.5 Transcribe
Gemini 3.5 Transcribe is a dedicated speech-to-text (transcription) model from Google DeepMind. A Sept 15, 2026 article reports it was "released last month." It provides transcription across 85+ languages and achieved reported average WERs of 4.0% (streaming) and 2.6% (non‑streaming). It is made available to developers via the Gemini API and Google AI Studio as part of Gemini Audio models.CURRENT SNAPSHOT3/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
ModalitySpeech-to-text (dedicated transcription model).
Word Error Rate (WER)Average WER reported as 4.0% (streaming) and 2.6% (non-streaming).
AvailabilityAvailable to developers via the Gemini API and Google AI Studio (as part of Gemini Audio models).
VERIFIABLE FACTS
Every value stays attached to a source and date.
RELEASE · ReleaseDEVELOPER CLAIM
Reported as "released last month" in a Sept 15, 2026 article.
MODALITIES · ModalityDEVELOPER CLAIM
Speech-to-text (dedicated transcription model).
CAPABILITIES · Multilingual coverageDEVELOPER CLAIM
Transcription across 85+ languages.
BENCHMARKS · Word Error Rate (WER)DEVELOPER CLAIM
Average WER reported as 4.0% (streaming) and 2.6% (non-streaming).
AVAILABILITY · AvailabilityDEVELOPER CLAIM
Available to developers via the Gemini API and Google AI Studio (as part of Gemini Audio models).
WHAT CHANGED