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.
- Released
- Aug 2026
- Pricing
- $0.005 per minute of audio
- Type
- Speech-to-text
- Languages
- Multilingual
- Timestamps
- Timed segments
- Speaker labels
- Supported
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.
Baseline accuracy and punctuation on clean speech
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.
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.
How dates, amounts, units and a surname are written out
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.
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.
Background noise, a second accent, speaker changes
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.
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.
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 ↗Google's most capable Gemini 4 reasoning model for the hardest coding, agentic, mathematical and scientific work, with text, image, audio and video input and a shared 1M-token context.
Google's fast, lower-cost Gemini 4 model for high-volume coding, agentic and multimodal work, with text, image, audio and video input and a shared 1M-token context.
Google's Gemini 4 tier between Hydrogen and Carbon, for complex coding, knowledge work and science at a lower price, with text, image, audio and video input and a shared 1M-token context.
Google's flagship reasoning model for complex software engineering, deep mathematical and scientific problem solving and autonomous multi-step agents, with a shared 1M-token context.
Google's most capable Flash model, with clear gains over 3.7 Flash in software engineering, agentic tasks, and multi-step reasoning, plus vision and a 1M-token context window.
Google's most efficient multimodal Flash model: an updated reasoning stack with stronger coding and computer-use quality, at the same speed and scale as the rest of the Flash line.