Google AI (@GoogleAI) on X (original) (raw)

Making AI helpful for everyone. Show thinking ↓

• Pinned
  
  Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy
  
• 
  Replying to @GoogleAI
  Read the blog to learn more:
• 
  Here’s this week’s shipping recap 👇 — Nano Banana 2 & Nano Banana Pro are now GA and available via the Gemini Enterprise Agent Platform, Gemini API, and in
  @GoogleAIStudio
  —Co-Scientist, our new multi-agent system for structured scientific thinking, generates and refines novel
• 
  Replying to @GoogleAI
  Read more about all the fun ways we used AI to bring I/O to life this year:
• 
  Replying to @GoogleAI
  Tune in for the full story ↓
• 
  Hear the architects of Gemini reflect on their journey to continue pushing the frontier of AI, on this episode of Release Notes.
  @JeffDean
  ,
  @koraykv
  ,
  @OriolVinyalsML
  , and
  @NoamShazeer
  sit down on camera together to share a behind-the-scenes look at the people behind the model,
  
• 
  Replying to @GoogleAI
  Draw a path that a drone can follow
  
  Gave google omni a sketched camera path and asked it to generate drone POV footage.
  
• 
  Replying to @GoogleAI
  Watch your avatar speak Spanish, English and Japanese
  
  Sigo jugando con Omni! Efectivamente el modelo desbloquea un montón de casos de uso (e.g. traducción) que antes requerían de concatenar varios modelos diferentes: Traducción → Voz cloning → Avatar lip-syncing... Ahora todo se reduce a un prompt
  
• 
  Replying to @GoogleAI
  Watch your avatar explore extreme jobs in extreme locations
  
  Round 2 with Gemini Omni. 🎬 This time, I tested identity consistency through pure absurdity. 20 extreme environments, 20 completely mismatched jobs. A corporate suit in the Amazon, a lifeguard in the Sahara, and a knight in the London Underground. Master prompt is in the
  
• 
  
  Cool video outpainting results with Gemini Omni
  
• 
  
  Google Flow is now powered by Gemini Omni. Upload your videos and edit them within the platform with the new Agent feature. It keeps the movement, audio and character intact whilst making edits in your scene. Here's a quick tutorial:
  
• 
  Replying to @GoogleAI
  Give yourself super powers
  
  Omni feels like magic 🤩
  
• 
  Some fun Gemini Omni use cases from the community 🧵👇