Skip to content
CSuite
Audio · Speech-to-text · Released Aug 2026

Google Gemini 3.5 Transcribe

Google's speech-to-text model for fast synchronous transcription with automatic language detection; this route returns plain text.

Gemini 3.5 Transcribe is a cloud speech-to-text model built by Google. It transcribes spoken audio into written text. It handles multiple spoken languages and can return timestamped segments along with the transcript. It also supports speaker labels and an optional text prompt that guides the spelling of names and terms. It runs through Google and OpenRouter using your own API key, from about $0.005 per minute of audio.

Modality
Audio
Available on
Model ID
google/gemini-3.5-transcribe
Specs
Released
Aug 2026
Pricing
$0.005 per minute of audio
Type
Speech-to-text
Languages
Multilingual
Timestamps
Timed segments
Speaker labels
Supported
Real outputs

Samples

Transcribed by Gemini 3.5 Transcribe via OpenRouter. The same three clips go to every speech-to-text model in the catalog, so the only thing that changes between two models’ transcripts is the model. The clips are synthetic speech made with ElevenLabs v4, and a word that differs from the spoken script is underlined. The numbers clip is left unmarked, since “12” and “twelve” are both right.

Plain dictation

Baseline accuracy and punctuation on clean speech

0:00 / 0:10

Thanks for joining on such short notice. We moved the launch to Thursday, so could you send me your notes before lunch? I will share the final schedule with everyone tomorrow morning.

TranscriptMatches the script

Thanks for joining on such short notice. We moved the launch to Thursday, so could you send me your notes before lunch? I will share the final schedule with everyone tomorrow morning.

Numbers and names

How dates, amounts, units and a surname are written out

0:00 / 0:19

Invoice 4471 is due on March 3rd, 2027. The total comes to $1,249.50 for 12 units, and the parcel weighs 2.5 kilograms. Please call Dr. Elena Markovic at 9:45 a.m. to confirm.

Transcript

Invoice 4471 is due on March 3rd, 2027. The total comes to $1,249.50 for 12 units, and the parcel weighs 2.5 kg. Please call Dr. Elena Markovich at 9:45 a.m. to confirm.

Two speakers over noise

Background noise, a second accent, speaker changes

0:00 / 0:13

Excuse me, is this seat taken? No, go ahead. Are you heading to the conference as well? I am. Do you know which stop it is? The one after the river, I think. We can walk over together.

TranscriptMatches the script

Excuse me, is this seat taken? No, go ahead. Are you heading to the conference as well? I am. Do you know which stop it is? The one after the river, I think. We can walk over together.

About the creator

Google

Google and Google DeepMind build the Gemini family of multimodal models, the Imagen and Nano Banana image models, the Lyria music models, and the Veo video models.

deepmind.google ↗
More from Google
Black Friday sale · 25% off

One-time payment. Yours forever.

No subscriptions. No renewals. Buy CSuite once, future updates included.

Secure checkout via Stripe. Already have a license? Download the app