gemini-live-api 开源项目推荐（98 个）

ZackAkil /immersive-language-learning-with-live-api

Immergo 是一款由 Google Gemini Live SDK 驱动的沉浸式语言学习应用。它模拟现实角色扮演场景（例如购买公交车票、点咖啡），帮助用户练习与作为母语者的AI交流。

addyosmani /jarvis

使用 Gemini Live API 构建的 JARVIS

coder-irwin /voice_ai_agents_using-Gemini_live_api

该项目在 GitHub 上没有填写描述

kkdai /gemini-live-translate-macos

基于 macOS ScreenCaptureKit 与 Gemini 3.5 Live Translate API 的会议实时语音口译与字幕翻译工具（Swift/SwiftUI）。

yogen-ghodke-113 /VoiceClaw

语音优先的 AI 结对程序员——与 Gemini 对话，由它指示 Claude Code 进行构建

kstonekuan /gemini-cli-voice-extension

Gemini CLI 的语音模式

pipedude /MadMax

Real-time voice AI agent with persistent memory, built on Gemini Live API and Python

IFA-AP-01 /gemini-live-translate-macos

Real-time speech translation & live captions for macOS meetings. Built with SwiftUI + Gemini 3.5 Live Translate + ScreenCaptureKit.

moshehbenavraham /Voice-Agent-PuPuPlatter

Multi-provider voice AI showcase featuring 8+ providers/services (ElevenLabs + Widget, OpenAI, OpenAI Live Translations, xAI, Ultravox, Vapi, Retell, Google Gemini Live) with real-time transcripts, audio visualization, and glassmorphism UI. Built with React 19 + TypeScript.

coder-irwin /ai-calling-assistant

Real-Time Voice AI Calling Assistant powered by Gemini Live API — native voice-to-voice, function calling, interrupt handling, zero backend

randombet /bodhi_realtime_agent

Real-time voice agents with parallel async background sub-agents — conversations continue naturally while tasks run • Join the builders → https://discord.gg/mqxKaN3UKC

geminidesktopwindows /Google-Gemini-Desktop

Google Gemini Desktop - AI, free download, 3.6 Flash, 3.7 Flash, 3.5 Pro, Deep Research, Gems, code. Windows Mac Linux. No subscription. Download:🡇

RakeshGowdaSN /Odyssey-AI

Odyssey-AI is an intelligent travel assistant that provides personalized travel plans, real-world photos, and AI-generated visuals for an immersive planning experience.

abubokkor-cse /EduMind-AI-Virtual-Teacher

AI Virtual Teacher with real-time lip-synced 3D avatars powered by Gemini Live API — voice conversation, image generation, smart quizzes, and deep research

hihumanzone /Gemini-Live-discord

A Node.js Discord bot that joins a voice channel, streams user speech to Gemini Live, and plays Gemini's streaming audio replies back into the same channel.

myned-ai /interactive-website-navigator

An interactive 3D Gaussian Splatting avatar that guides website visitors using real-time voice, screen awareness, and action taking — powered by Gemini Live API on Google Cloud.

moshehbenavraham /chat_with_google_maps

Voice AI Conversation with Google Maps

usufalbaz /teachme-ai

gemini-live-api, speech-recognition, english-coach, phonetics, react19, typescript, tailwindcss, firebase-firestore, pwa, websockets, arabic-tutor

vero-code /spatial-engine

Spatial Engine AI: A DeepTech Agent that sees like a designer and calculates like a physicist. Powered by Gemini 3 Pro & Vision to optimize energy efficiency in built environments.

Iamsdt /audiocall

Open source AI voice calling agent for Twilio phone calls, built with FastAPI, Google ADK, and Gemini Live API