Voice assistants & voice agents
995 agents · most starred first
Voice assistants & voice agents, page 4 of 10
A machine learning powered, voice-based virtual assistant for Raspberry Pi. Supports several features like conversation, weather, opening websites, geolocation, date/time, and creating timers.
Let your AI agent call your phone and talk to you — MCP servers for live, interruptible voice calls + tiered alerts, using free self-hosted pieces (pjsua2 + whisper.cpp + Linphone). No paid telephony, no extra API key.
Example realtime voice agent built with Google ADK and deepagents
🔊😊 A fastapi voice-assistant framework to quickly prototype LLM-powered voice assistants in <5 minutes.
Full-stack LiveKit voice agent starter: a Python voice worker, FastAPI token server, and React frontend. Run, deploy, and swap each piece on its own. Ask for ShipVoice pro
Offline voice-agent application layer: session core with byte-deterministic replay, spoken-LLM adapters (scripted/replay/loopback-mock), injection-safe function-call grammar, slot grounding, workflow engine with compensation and resume, permissioned tool sandbox, repair-dialog policies, task-success and latency evaluation. NumPy core, torch extra.
A multimodal agent built with Python agents framework
Voice2voice ChatGPT Assistant built through OpenAI Whisper (speech2text) + OpenAI ChatGPT API + Google Text2Speech Service (text2speech)
Self-hosted multilingual (English + 5 Indic) phone voice agent template - LiveKit Agents + Sarvam STT/TTS + OpenAI + Vobiz SIP. ~700ms-1.2s latency, under Rs 5.5/min. Demo: a real-estate site-visit booking agent.
Self-hosted AI voice agent for Asterisk. Streaming STT to LLM to TTS over AudioSocket, with barge-in and tool calling.
Local-first voice memory assistant — capture speech, transcribe live, and ask a private RAG chatbot grounded in what you've actually said. No cloud required.
SPLAA is an AI assistant framework that utilizes voice recognition, text-to-speech, and tool-calling capabilities to provide a conversational and interactive experience. It uses LLMs available through Ollama and has capabilities for extending functionalities through a modular tool system.
CopperAI offers a hands-free, voice-to-voice interaction system with a Large Language Model (LLM)
Free OpenAI voice/audio interfacing package for Python
A repo listing known open source voice tools, ordered by where they sit in the voice stack
A sophisticated AI-powered voice assistant that handles incoming phone calls and provides a web-based chat interface. Built with TypeScript, Fastify, and OpenAI's Realtime API, this system integrates with Twilio for telephony services and includes advanced features like memory management, calendar integration, and webhook-based data processing.
This is the guide to show the method to build your own AI-Powered voice agent with LiveKit and Twillio
Open Source TypeScript SDK for building real-time multimodal voice & vision AI agents
This project registers a Python SIP client as an extension in Asterisk/FreePBX and connects calls to OpenAI Voice Agent in real-time using WebSocket.
A voice-to-voice conversation with ChatGPT. Support for talking through a NAO robot
Библиотека - готовый каркас для голосового/текстового чата с OpenAI Realtime (WebRTC + DataChannel) в React Native.
Monika is an AI assistant that combines speech-to-text, natural language processing, and text-to-speech capabilities for seamless interaction.
La cara y la voz de tu agente de IA en una pantalla redonda de Waveshare (ESP32-S3 AMOLED 1.75 · ESP32-P4 4C). Hermes Agent, Whisper, Piper. Personalízalo con Claude Code.
Zippy Talking Avatar uses Azure Cognitive Services and OpenAI API to generate text and speech. It is built with Next.js and Tailwind CSS. This avatar responds to user input by generating both text and speech, offering a dynamic and immersive user experience
Design, train, and orchestrate AI voice agents in a single dashboard, then connect them to your preferred ASR, LLM, TTS, or real-time speech providers with just a few clicks. The guided workflows eliminate complex setup so teams of any size can go from idea to production-ready agent in record time.
中文语音助手 | 唤醒词 + ASR + OpenClaw Agent + TTS | 离线唤醒、流式语音交互、工具调用、Skills 扩展
Interactive Voice interface with tool use for Obsidian. It's like ChatGPT's Live mode, with access to your vault. With bring your own API key.
Voice agent using LiveKit (orchestration), Cartesia (STT + TTS), and OpenAI (LLM)
Enhanced Voice Assistant, Works with both terminal and API, Multimodal, Multilingual, Modular design. Supports Voice ID, Face recognition, and configurable tools. Built-in Chatgpt, Claude, Deepseek, Gemini, Grok, and Ollama. Explore the possibilities of Human-AI interactions
🤖 A text-to-speech chatbot built using Nextjs, OpenAI, and ElevenLabs.
Your AI assistant, stt -> llm agent -> tts, full api, can run on raspberry pi
Engaging in conversation with ChatGPT using voice.
Minimalist speech2speech implementation with Twilio and OpenAI Realtime
This is 3D Avatar chat bot based on Open AI GPT3, and google Text to speech integration and oculus lipsync. you feel like you are interacting with real chat agent
A sophisticated real-time voice assistant that seamlessly integrates speech recognition, AI reasoning, and neural text-to-speech synthesis. It is designed for natural conversational interactions with advanced tool-calling capabilities.
Build realtime AI interviewer voice agent that joins meetings. It demonstrates integrating Deepgram (STT), OpenAI (LLM), and Eleven Labs (TTS) via WebRTC for natural conversations.
This project is the backend engine for a fully autonomous AI-powered call center. It integrates a large language model (LLM), speech recognition, and text-to-speech to manage real-time phone conversations via Asterisk.
Voice to brain interface 🦞🎤🧠 for OpenClaw, Hermes, PI, etc
Build, share, and talk to autonomous Voice Agents powered by Vapi & ElevenLabs. (Built as a part of Vibe Coding Hackathon)
Flutter: A mobile assistant app utilizing OpenAI GPT and ElevenLabs Voice Text-To-Speech API's.
I Built an AI Receptionist That Books Appointments (Claude SDK + Vapi)
Voice controlled ChatGPT for iOS using Shortcuts with temporary memory to carry extended conversations
Introducing Eliza! A low-latency, human-like conversational AI with memory and the ability to handle interruptions ✨
Enterprise-grade browser extension bringing multilingual voice interaction to AI chatbots (Pi, Claude, ChatGPT). Features real-time speech detection with Silero VAD, accurate transcription via OpenAI Whisper, and ElevenLabs TTS. Built with TypeScript, XState, and modern web standards. Progressive enhancement across Chrome, Firefox, and Safari
AI-powered telephony solution that enables businesses to deploy intelligent voice agents for various use cases such as customer support, appointment scheduling, lead qualification, and information collection.
かわいいキャラと声になってライブ配信・かわいいAIエージェントとおしゃべりWebサービス基盤(全部オンプレ運用可能)
HIPAA-eligible DIY Twilio alternative for voice AI telephone applications. Uses Asterisk PBX and AWS Chime SIP trunking.
A video-call avatar frontend for your local LLM agent (Hermes/OpenClaw) — replaces the messenger chat and serves the agent's exact slash-command menu. Open-core engine: emotion, mood, voice, build-your-own-avatar pipeline. GPU-free · MIT.
Turn Claude Code into a voice-enabled, multi-channel assistant that runs tasks in parallel
The Personal Voice Assistant is a sophisticated AI-driven tool designed to interact with users through natural language. Leveraging a state-of-the-art language model (LLM), this assistant provides a seamless and intuitive experience by understanding and executing functions.
Desktop voice interface for Codex, with project switching, interruption, steering, and approval forwarding through OpenAI Realtime and Codex app-server.
Self-hosted AI voice server for StackChan ESP32-S3 robots, supporting Home Assistant and standalone Docker with OpenAI Realtime, Gemini Live, and OpenAI-compatible providers.
Self-hosted voice AI agents with a Vapi-compatible API. AI phone agents on Twilio, Telnyx, Plivo, Vonage or SIP, with your keys or 100% local and free (Whisper, Ollama, Kokoro). No per-minute platform fee. npx openring
Voice Assistant using Google's Gemini API Key
A voice remote for AI agents: push-to-talk, procedural avatar + live status ring on the M5Stack StopWatch (ESP32-S3 round AMOLED). Hermes gadget firmware, hub plugin, desktop sim, WiFi OTA.
让 AI 用自己的手机和号码打真实电话:ESP32 蓝牙桥接,中文控制台,豆包 / OpenAI,Prompt、录音总结与主动重连。
Book appointments, record messages, get information and much more via voice through Pam AI, an Auto-GPT like AI receptionist.
Telephony Server is a powerful bridge that connects telephony providers (Twilio, Vonage, Plivo, etc.) with real-time communication platforms (LiveKit, Jay.so, Pipecat, etc.). It enables seamless call routing, robust metrics collection, and observability features for enhanced telephony operations.
Chat with your RVC models. See website for demo:
This repository contains an attempt to incorporate Rasa Chatbot with state-of-the-art ASR (Automatic Speech Recognition) and TTS (Text-to-Speech) models directly without the need of running additional servers or socket connections.
Model uses Whisper, CHATGPT, GTTS
A Voice-to-Voice AI Agent that lets you naturally talk to documents in real time. Powered by LiveKit's ultra-low-latency STT → LLM → TTS pipeline, it uses RAG for instant document insights and Redis for persistent memory—delivering a fully immersive voice-first experience.
Talk to ChatGPT using your voice, and have it respond back to you with a voice. You can now talk to GPT using your voice or through the text field.
数字心屿|AI 情绪陪伴数字人 一款多模态大模型驱动的智能情感陪护数字人系统。基于FunASR+MediaPipe+Qwen2.5-14B+CosyVoice+Live2D,实现语音识别~情感对话~数字人实时驱动。支持自然语音与文字对话、Live2D 表情互动、心理学知识检索和用户可控的长期记忆,适配桌面与移动端。赛题A22|团队T2607288
AI Infrastructure Engage & Think Layers for Voice & Vision Interactions
A FastAPI application that relays client WebSocket connections to OpenAI's Realtime API, enabling seamless integration for real-time speech-to-speech interactions
A powerful AI Agent Demo playground that combines the intelligence of AI agents LLM with real-time speech-to-speech models integration. Build sophisticated voice-enabled applications for customer service, sales automation, and interactive assistants.
GLaDOS Terminal-based AI Assistant
Open-source realtime voice AI with adaptive VAD, latency telemetry, interruptible TTS, an inspectable TypeScript WebSocket gateway, and experimental Ollama/local AI.
Just a simple multimodal avatar interaction platform
Speech-to-Speech conversational AI using Azure OpenAI Service and Azure Speech Services
Zero-Infrastructure Lip-Synced 3D avatar components for AI voice agents. This library is built with React Three Fiber and AI providers
跨平台桌面语音工作台:在任意应用里说、译、听 / A cross-platform voice workspace for your desktop: dictate, translate, and listen in any app
A pocket ESP32-S3 AMOLED charm with a living character on it: hold to talk to your AI agent (Hermes or any OpenAI-compatible model), glance at what's waiting, hold to say yes.
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
Ashley 桌面语音助手 · 类贾维斯(Jarvis)AI 助手 · 全双工实时语音 + 3D 头盔 · macOS 开源 | macOS desktop voice assistant with a 3D avatar
Jarvis like chatbot with voice
Python Voice-Chatbot with offline voice recognition.
Medora AI is an innovative, voice-first medical appointment booking system designed to revolutionize healthcare scheduling through conversational artificial intelligence
Headless Matrix WebRTC voice AND video agent — auto-answers calls, bridges audio to any AI agent via PipeWire, optional camera-frame vision for multimodal LLMs
docker region:us
Voice Agent implementations for the VAmoS Benchmark
Voice agents in YAML, compiled to Pipecat or LiveKit. Production code you own, deployed anywhere.
Single-file example on how to use the OpenAI Realtime API with WebRTC
An Alexa skill providing a conversational interface to any public figure (as mimicked by GPT3). The legacy GUI is no longer maintained.
Outbound PSTN calling agent using LiveKit SIP trunks with a voice pipeline (Silero VAD, Deepgram STT, OpenAI LLM+TTS). Includes a simple CLI for local development, health checks, and model prewarming.
Agentic voice AI using ConversationRelay. 5 minute setup.
Desktop realtime speech translator for routing translated audio between virtual audio devices in calls.
TypeScript SDK and CLI for building AI agents that autonomously join, listen, and speak in X/Twitter Spaces. Supports multiple LLM providers (OpenAI, Claude, Groq), speech-to-text (Whisper, Deepgram), text-to-speech (ElevenLabs, OpenAI), multi-agent coordination, middleware pipelines, and a real-time admin dashboard. No Twitter API approval needed
Voice calling plugin for OpenClaw — give your AI agent a phone number. Inbound/outbound calls, batch calling campaigns, SMS, post-call transcripts & notifications, ElevenLabs + Deepgram voice engines.
Real-time voice AI agent with persistent memory, built on Gemini Live API and Python
MeetAI is an AI-powered conversational platform that enables real-time voice interactions with context-aware agents using modern web technologies and scalable cloud infrastructure.
AI voice assistant that answers your phone calls with a human-like persona, speaks naturally in many languages (GPT-4o + ElevenLabs) and keeps you in the loop via Signal with real-time mid-call instructions.
Voice-to-Voice Chatbot using Whisper, LLaMA, and Groq API
OpenAI-Assistant API integration with Speech Recognition and Eleven Labs TTS. User can choose name, description, model of assistant and ElevenLabs Voice. Speech recognition with Azure.
End-to-end AI-powered video call application where you implement real-time calls with customized AI agents, generate automatic summaries and transcriptions through background processes, and create a post-call experience with video playback, transcript search, and a contextual AI chat. The project also covers authentication, subscriptions, etc
Open source voice bot for Humanoid Robots and virtual digital humans
voice ai agent that's able to do tool calls with composio integrations
WhisperMesh is an advanced chatbot that integrates voice and text interactions, delivering personalized responses through LLM models and a sophisticated vector database. Leveraging the RAG framework from Haystack, it ensures engaging, data-driven conversations that adapt to your preferred style.