Subvolts take Google's Gemini Live API unlocks real-time audio interfaces for developers. Aug 6, 2025 - Developers
- Learn how to build real-time, audio-first applications using Google's Gemini Live API and its advanced features.
- Business
- Understand how new AI audio interfaces can create more engaging and responsive customer experiences.
This episode provides a detailed look at a specific developer tool from a major AI lab, explaining its features and potential applications.
Building real-time voice applications with Live API
Audio streams from Google AI. Your place is remembered on this device.
From Subvolts
Summary and analysis by Subvolts editorial, AI-assisted.
Google AI: Release Notes host Logan Kilpatrick interviews Shrestha Basu Mallick about the Gemini Live API. This real-time, multimodal interface allows developers to build applications using native audio, proactive audio, and asynchronous function calling. The discussion covers the API's capabilities, developer use cases, and future roadmap, highlighting audio as a unique interface modality.
This episode explains Google's new Gemini Live API, which lets developers build apps that use sound in real-time. Imagine apps that can listen and respond instantly, making interactions more natural and powerful. It's for anyone interested in how AI can understand and use voice.
This episode offers developers a deep dive into Google's Gemini Live API, a tool for creating real-time, multimodal applications. It explains how to leverage audio as an interface, a growing area for AI. Listeners will learn about proactive audio, async function calling, and the API's roadmap. This is relevant as major AI labs focus on multimodal interactions and developer tools to expand AI's reach beyond text.
- HostLogan Kilpatrick
- GuestShrestha Basu MallickProduct Lead for the Gemini API, Google
- Episode Title: Building real-time voice applications with Live API
- Show: Google AI: Release Notes
- Length: 40 minutes
- Guest: Shrestha Basu Mallick, Product Lead for the Gemini API
- Key Feature: Gemini Live API: real-time, multimodal interface
- Key Capabilities: Native audio, proactive audio, async function calling
Shrestha Basu Mallick, one of the product leads for the Gemini API, joins host Logan Kilpatrick for a deep dive of Gemini Live API, Google’s real-time, multimodal interface for developers. Learn about how native audio alongside new capabilities like proactive audio and async function calling unlocks the unique power of audio as an interface.
Watch on YouTube: https://www.youtube.com/watch?v=4xlwlU6h-wM
0:00 - Intro
1:18 - Live API Overview
3:36 - Why audio is a special modality
5:07 - Speed vs. precision in audio
6:17 - Controllable and promptable TTS
8:31 - What developers are building with the Live API
11:14 - URL context and async calling features
15:02 - Proactive audio and affective dialog
16:55 - Addressing developer feedback
21:54 - Live API roadmap
23:49 - The role of long context
24:57 - What’s next for the Live API
26:41 - State of the AI audio market
30:10 - Advice for developers getting started with the Live API
31:16 - Live API demo
38:10 - Demo wrap up and closing
- multimodal
- Shrestha Basu Mallick
- able to understand and use different types of information, like text, images, and sound.
- proactive audio
- Shrestha Basu Mallick
- audio that can anticipate user needs or provide information without being explicitly asked.
- async function calling
- Shrestha Basu Mallick
- allowing a program to perform tasks in the background without stopping other operations.
27 minKoray Kavukcuoglu on frontier models, coding agents, and building AGI
WithKoray Kavukcuoglu
39 minIntroducing Gemini Robotics 2
WithCarolina Parada, Stuart Bowers, Kanishka Rao, Jie Tan
42 minGemini co-leads on project origins and what's next
WithJeff Dean, Koray Kavukcuoglu, Noam Shazeer, Oriol Vinyals
40 minQuestions people ask
- What is the Gemini Live API?
- It is Google's real-time, multimodal interface for developers, enabling native audio and new capabilities like proactive audio and async function calling.
- What can developers build with the Live API?
- The episode discusses how developers are building applications that leverage audio as a unique interface modality, unlocking new interaction possibilities.
Page generated Oct 19, 2026. Summaries are Subvolts' own; the audio, artwork and notes belong to Google AI.