# Gemini Live audio

DevFeed: [Gemini Live audio](<https://devfeed.tech/articles/gemini-live-audio-31180.md>)

Original publisher: [Read original article](<https://simonwillison.net/2026/Sep/15/gemini-live/>)

Author: Simon Willison

Published: 2026-09-15T22:47:07Z

Content type: tutorial

Language: en

Sources: [Simon Willison's Weblog](<https://devfeed.tech/sources/simon-willison-s-weblog.md>)

Topics: [speech-to-speech](<https://devfeed.tech/topics/speech-to-speech.md>), [WebSocket](<https://devfeed.tech/topics/websocket.md>), [Google AI](<https://devfeed.tech/topics/google-ai.md>), [browser](<https://devfeed.tech/topics/browser.md>), [Playback](<https://devfeed.tech/topics/playback.md>), [implementation](<https://devfeed.tech/topics/implementation.md>), [API](<https://devfeed.tech/topics/api.md>)

Tags: [api](<https://devfeed.tech/tags/api.md>), [audio](<https://devfeed.tech/tags/audio.md>), [browser](<https://devfeed.tech/tags/browser.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-196](<https://devfeed.tech/tags/gemini-196.md>), [generative-ai](<https://devfeed.tech/tags/generative-ai.md>), [generative-ai-1-982](<https://devfeed.tech/tags/generative-ai-1-982.md>), [google](<https://devfeed.tech/tags/google.md>), [google-416](<https://devfeed.tech/tags/google-416.md>), [llm-release](<https://devfeed.tech/tags/llm-release.md>), [llm-release-231](<https://devfeed.tech/tags/llm-release-231.md>), [llms](<https://devfeed.tech/tags/llms.md>), [llms-1-948](<https://devfeed.tech/tags/llms-1-948.md>), [model](<https://devfeed.tech/tags/model.md>), [models](<https://devfeed.tech/tags/models.md>), [openai](<https://devfeed.tech/tags/openai.md>), [playback](<https://devfeed.tech/tags/playback.md>), [release](<https://devfeed.tech/tags/release.md>), [speech-to-speech](<https://devfeed.tech/tags/speech-to-speech.md>), [speech-to-text](<https://devfeed.tech/tags/speech-to-text.md>), [speech-to-text-21](<https://devfeed.tech/tags/speech-to-text-21.md>), [tools](<https://devfeed.tech/tags/tools.md>), [tools-78](<https://devfeed.tech/tags/tools-78.md>), [ui](<https://devfeed.tech/tags/ui.md>), [voice](<https://devfeed.tech/tags/voice.md>), [websocket](<https://devfeed.tech/tags/websocket.md>), [websockets](<https://devfeed.tech/tags/websockets.md>), [websockets-21](<https://devfeed.tech/tags/websockets-21.md>)

## AI overview

The article describes a browser-based web UI for trying Google's Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking speech-to-speech models. The implementation supports model and voice selection, an optional system prompt, voice conversations, and interruption while the model is speaking. It uses no libraries, connecting to a WebSocket endpoint and using the Web Audio API for capture and playback.

## Source excerpt

Tool: Gemini Live audio Google released Gemini 3.8 Live and 3.8 Live Extended Thinking today - two new speech-to-speech models that are a similar shape to OpenAI's GPT-Live family. I pointed GPT-6 Astra Extra High at the documentation and had it build me this web UI for trying out the new models. You can select a model and voice preset, enter an optional system prompt and then start a voice conversation through your browser, including the ability to interrupt the model while it is talking. The implementation uses no libraries. It connects to the wss://generativelanguage.googleapis.com/ws/google.ai.generativelanguage.v1alpha.GenerativeService.BidiGenerateContent?key=... WebSocket endpoint and uses a Web Audio API AudioContext for both capture and playback. Here's the Gemini Live tutorial for getting started with that WebSockets API. Tags: google, tools, websockets, generative-ai, llms, gemini, llm-release, speech-to-text