← kwindla hultman kramer

This overview from Google walks through the new features in the Multimodal Live…

April 23, 2025

This overview from Google walks through the new features in the Multimodal Live API: more control, flexibility, and longer sessions. There's been so much developer interest in this API. It's great to see this continuing evolution.

The blog links to the Word Wrangler game that @mark_backman and @JonPTaylor wrote to explore building complex game flows with the Multimodal Live API. Check out both the blog post and the game, if you're interested in voice AI ...

Shrestha Basu Mallick@shresbm

New blog out going into a little more detail on what we support with the Live API in its latest incarnation!

We discuss
πŸͺ› Knobs you can use to increase session length
πŸ”Š How to control voice activity detection
πŸ§‘β€πŸ€β€πŸ§‘ 3 great demos from our partners @trydaily

Play the game[1]

Read the architecture notes and clone the repo[2]

  1. https://word-wrangler.vercel.app/ ↩
  2. https://github.com/daily-co/word-wrangler-gemini-live ↩