Voice assistants & voice agents
Voice assistants and voice agents hold real-time spoken conversations, handling speech recognition, turn-taking, and spoken replies, often over phone calls or live audio streams. Frameworks like pipecat and ten-framework focus on the plumbing that connects models and audio transport, while others target specific pieces such as low-latency transcription or Chinese-language dialogue.
995 agents · most starred first
Top 100 of 995
Open Source framework for voice agents, multimodal apps, and realtime AI. Maintained by Daily and the community.
A framework for building realtime voice AI agents 🤖🎙️📹
Build voice agents with open-source models
Very low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces
Open-source framework for conversational voice AI agents
AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Quickly build text, voice and video agents. Fast, Go based Agent backend with SDKs for every language. Sensible defaults for search, knowledge, skills, telephony, sandboxes, memory and persistence. Sovereign AI. Take control of your AI.
🤖 wukong-robot 是一个简单、灵活、优雅的中文语音对话机器人/智能音箱项目,支持ChatGPT多轮对话能力,还可能是首个支持脑机交互的开源智能音箱项目。
This is a simple demonstration of more advanced, agentic patterns built on top of the Realtime API.
Send a phone call from AI agent, in an API call. Or, directly call the bot from the configured phone number!
The #1 open-source voice interface for desktop, mobile, and ESP32 chips.
🤖 Build voice-based LLM agents. Modular + open source.
React app for inspecting, building and debugging with the Realtime API
A realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
Infrastructure for the next generation of voice agents, designed to provide universal memory. It is divided into a left brain and a right brain, storing information and emotions respectively, while a fully streaming architecture eliminates latency at the fundamental level.
💬 SpeechGPT is a web application that enables you to converse with ChatGPT.
Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin
Voice AI SDK is a reusable Android library that gives any app a full voice-driven AI conversation pipeline in minutes. Voice Assistant + Android Voide AI + SDK + MVVM + Kotlin
Baresip is a modular SIP User-Agent with audio and video support
OpenVidu Platform: self-hosted real-time video and audio for your apps, built on LiveKit and mediasoup
Realtime Voice AI with 100+ Models on Arduino ESP32 with Secure Websockets & Edge Functions for AI Toys, Desk Companions and Devices
Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
The Self-Coding System for Your App — Alan AI SDK for iOS
百聆 是一个类似GPT-4o的语音对话机器人,通过ASR+LLM+TTS实现,集成DeepSeek R1等优秀大模型,接入openClaw,真正的个人语音助手,时延低至800ms,Mac等低配置也可运行,支持打断
一个基于小智、xiaozhi-server的Android、IOS语音对话应用,支持实时语音交互和文字对话。现在是flutter版本,打通IOS、Android端。请同志们动动小手,点点小星星,予以鼓励。
Real-time two-way speech translation for bilingual meetings — auto-detects the spoken language and translates both directions, cloud or fully offline on-device. Desktop (Windows · macOS · Linux) + browser extension (Chrome · Edge) for Zoom, Meet, Teams & any app.
Natural voice conversations with Claude Code
An AI-powered interactive avatar engine using Live2D, LLM, ASR, TTS, and RVC. Ideal for VTubing, streaming, and virtual assistant applications.
ChatdollKit enables you to make your 3D model into a chatbot
An open-source AI Voice Agent that integrates with Asterisk/FreePBX using Audiosocket/RTP/Websocket technology https://demo.agent6789.com
The Self-Coding System for Your App — Alan AI SDK for Cordova
AI Vtuber for Streaming on Youtube/Twitch
Build realtime AI voice agents using FastRTC for low-latency streaming, Superlinked for vector search, Twilio for live phone calls, and Runpod for scalable GPU deployment.
Open-source voice-AI SDK. The Vapi/Retell alternative for builders who want to own the stack. Give your AI agent a phone number in 4 lines — Python and TypeScript, MIT licensed, Twilio, Telnyx, and Plivo.
AI phone assistant | open-source
Node.js + JavaScript reference client for the Realtime API (beta)
JARVIS — a voice assistant for Claude Code. Talk to your Mac and he brainstorms a project with you, builds it, and tells you out loud when a Claude Code session needs you. macOS, on your Claude subscription, no API key.
A complete voice AI frontend app for LiveKit Agents with Next.js
A talking LLM that runs on your own computer without needing the internet.
Build realtime multimodal AI agents with Node.js
Open-source real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.
Conversational voice AI agents
Command Your World with Voice
Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit
Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.
Local AI talk with a custom voice based on Zephyr 7B model. Uses RealtimeSTT with faster_whisper for transcription and RealtimeTTS with Coqui XTTS for synthesis.
Self-hosted API-first AI call center: AI talks, code controls the call. AI agents answer every call; humans take over without dropping it. Runs on FreeSWITCH with your SIP trunk and realtime model (OpenAI, Grok, Qwen, Doubao, or any compatible gateway).
Example scripts for AI agents created with the Alan AI Platform.
Multi-modal voice agent for your AI agents. Talk with Claude Code, Codex, and others by voice: answer their prompts, give instructions, ask what they did. Or just nod.
Open Source Voice Agent Platform
A conversational, AI device + software framework for companionship, entertainment, education, healthcare, IoT applications, and DIY robotics. Built with Python, NextJS, Arduino, ESP32, LLMs (GPT-4o), Deepgram STT and Azure TTS 🤖
Pocket-sized AI chatbot built using a RPI Zero 2w / 5
Your own personal voice assistant: Voice to Text to LLM to Speech, displayed in a web interface
Mac compatible Ollama Voice
Open-source, self-hostable platform for building and operating AI phone agents.
Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.
Gemini Live provides multimodal realtime agent capabilities. Build voice agents that can process vision and text in realtime.
Build an AI Telephony Agent for Inbound and Outbound Calls
A Conversational Assistant equipped with synthetic voices including J.A.R.V.I.S's. Powered by OpenAI and IBM Watson APIs and a Tacotron model for voice generation.
😆 A voice chatbot that can imitate your expression. OpenCV+Dlib+Live2D+Moments Recorder+Turing Robot+Iflytek IAT+Iflytek TTS
Let your AI agents call your phone over VoIP, and call them back. Your phone rings like a real call, even locked; a voice AI talks it through and returns the transcript. Self-hosted, open source, no phone numbers or Twilio.
Your personal voice assistant based on OpenAI ChatGPT.
Leverage the OpenAI Realtime API (12-17-2024) with this Next.js 15 starter template featuring shadcn/ui components, tool-calling & localization. Use starter to build Voice AI apps with WebRTC.
a open-source Artificial Intelligence Virtual Youtuber (AI VTuber), (this project is deprecated)
End-to-end platform for building voice first multimodal agents
JARVIS V4 · Mac ve Windows için ücretsiz sesli yapay zekâ asistanı (Gemini Live). İndir: Releases
Give a face to your voice AI in 5 lines of code. Generate realtime avatar video connected to your voice AI locally
Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.
Stream-Omni is a GPT-4o-like language-vision-speech chatbot that simultaneously supports interaction across various modality combinations.
say - command line tool for voice and video calling
TypeScript client for OpenAI's realtime voice API.
Pipecat voice AI agents running locally on macOS
Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖
Build realtime voice and video agents with Google's new Gemini 2.0 (API is free for now)
Demonstrates how to protect your OpenAI API Key using a Cloudflare Worker to serve your ephemeral token and then do client side tool calling
Low latency ai companion voice talk in 60 lines of code using faster_whisper and elevenlabs input streaming
Runnable examples for LiveKit Agents in Python
This AI Smart Speaker uses speech recognition, TTS (text-to-speech), and STT (speech-to-text) to enable voice and vision-driven conversations, with additional web search capabilities via OpenAI and Langchain agents.
Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks
A complete voice AI building block with telephony integration, featuring real-time speech-to-text, text-to-speech, and LLM-powered conversational agents.
Allows you to have an engaging and safely emotive spoken / CLI conversation with the AI ChatGPT / GPT-4 while giving you the option to let it remember things discussed.
Private voice keyboard, agent, AI chat, images, webcam, recordings, voice control with >= 4 GiB of VRAM.
Firefox Voice is an experiment in a voice-controlled web user agent
World's First Multilingual Inexpensive Therapeutic Sophisticated Ultra-responsive Holographic Agent. In simple terms, an AI you can talk to and it'll talk back with a body using VTube Studio.
A complete voice AI starter for LiveKit Agents with Python.
Multilingual Inexpensive Therapeutic Sophisticated Ultra-responsive Holographic Agent. In simple terms, an AI you can talk to and it'll talk back with a body using VTube Studio.
Talk to ChatGPT in real time using LiveKit
Open-source MCP server for safe, stateful AI-agent phone calls with OpenAI Realtime and Twilio.
Sample application to add voice capabilities to the Agents SDK
A multi-model Muse: personal AI voice assistant on ESP32 - wake word or knob, any OpenAI-compatible brain (STT/chat/TTS mix-and-match), streaming replies, out of the box. Built on muse-gadget-sdk.
Your voice-controlled Mac assistant
Open-source realtime voice agent server in Go with WebRTC (WHIP), barge-in, streaming STT/LLM/TTS pipelines, plugin system, multi-language SDKs, SIP telephony, ESP32 support & fully local mode.
Daily Bots Web Demo showcasing how to build real-time voice AI agents
OpenAI-Compatible Proxy Middleware for the Wyoming Protocol
DaVinci - The GPT-Realtime-2.1 Talking AI Virtual Assistant - New Version Fall 2026
Samantha OS1 is a conversational AI assistant powered by the Realtime API from OpenAI
AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)
Hermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini. Terminal, Discord, dashboard.
Full stack voice chatbot