Ting-Wei Chu   •   3 months ago

Gemini send_realtime and send_conten API question

Can the Gemini model take the input from send_realtime and send_content simultaneously for a combined reasoning?

• 1 comment

  Email me when new comments are added
• 

  Dileep Kumar Sharma   •   3 months ago

  Hey,

  Yes, the Gemini Live session maintains context across both input methods. You can send audio via `send_realtime` and text via `send_content` to the same session, and the model reasons over the combined context. In our project we use both voice and text input to the same Live session and the model tracks the full conversation regardless of which input method was used for each turn.

Log in or sign up for Devpost to join the conversation.