Introducing Gemini 3.5 Transcribe, our most precise speech-to-text model yet, designed for intelligent voice interactions! 💬 Available for both real-time speech and audio file transcription, with support for: 💡 smart transcription: rewrite and format text based on intent. 🌍 support for 85+ languages, regional accents and diverse dialects. 📚... custom vocabulary: recognize jargon and specific spellings. 💯 high precision in alphanumerics. 🫂 multi-speaker identification.show more

amazing working getting this model out : )

Thanks, Logan 🫶 So excited to see what folks will build 🚀

Available now on the Gemini API, @GoogleAIStudio, and many other awesome products like Gboard, @antigravity, the Gemini app, and @googlechrome!

So cool!

Multi speaker is huge 🗣️

Tour dates for debut album wen?

Catch me in Buenos Aires soon!

Google AI Edge Eloquent became the local AI app i can’t recommend enough to those i know as it’s the first thing i launch on my phone & mac. hope this gets integrated into the app in some way

Seems to be super smart.

It must be if it can understand my German 😳

This is nice

Is this what you were talking about yesterday, or is there more to come? I really don't want to lose faith in Google, but they still haven't released the model they promised about two months ago

Please add computer vision for sign language!

Custom vocab plus diarization is the meeting-notes combo. 🫡

Real-time transcribe looks great, but shoutout to the timely edits!

amazing how every time i saw you present something it's a new transcription model 🫶 unfortunately this one is not good enough because it cannot codeswitch tried with English, French and Romanian and it only detected Romania

Will it be used for Gemini live? Currently speech transcription is pretty bad even though the model understands the audio well!

Good

Word level Timestamps too? Comparison to whisper and deepgram?

@googledevs Dear sir, I am a non English native speaker but you sound like from the UK, do you?

Mutlispeaker identification is epic!

Now THIS is impressive! Might need to add this into instead of the current transcription tooling I am using. I for sure thought "Unary" would make be a mistake and that would have still be passable but this is good.

Would be great if you could do a follow up on how to enable (configuration/fine tuning/post training) intent based transcription for medical and technical research use cases

Whoah, Xerox and IBM vibes. A dying giant. You had literally everything to achieve AGI, and now you cannot even deliver Gemini 3.5 Pro. After this 3.5 Transcribed was announced, Google stock price went down another 1%.

It's pretty solid! Kudos team! It can even clean up the interfering speech by itself. Tried to give it some hard time, but it did pretty well. 💪