Self-hosted AI voice agent

Build Phone Calling Voice Agent fully powered by open source models.

AI Voice Assistant: Talk to an AI agent that helps you with event scheduling, contact management, accessing your knowledge base, and web searches using simple voice commands

🤖 Jarvis - AI Voice Assistant with Face Recognition | Hacktoberfest 2025 Friendly | Built with Python, OpenCV, and Modern Web Technologies

Oasis-InfoByte-Python-Internship-Solution

🇷🇺 Russian Voice AI : 📞 Локальный AI-секретарь с клонированием голоса XTTS v2, real-time распознаванием речи (Vosk/Whisper) и offline LLM (vLLM + Qwen/Llama и тп). Полноценная админ-панель (Vue 3), Telegram-бот, виджет для сайта, fine-tuning pipeline. Self-hosted, приватность данных, СМС и телефонные звонки .

A collection of intelligent AI agents built using Ollama, LangChain, and local LLMs, including chatbots, voice assistants, web scrapers, document readers, and specialized tools. No API required. Fully autonomous and privacy-preserving.

A Pipecat Starter Kit that uses the Pipecat React Pipecat SDK and Vapi Blocks

A real-time AI speech coach for children, built with LiveKit Agents and Google Gemini Flash 2.0. Focused on personalized pronunciation practice through dynamic character, language, and activity selection.

The Wonderful Wino addon provides a user-friendly interface to manage your wine collection within Home Assistant. It utilizes the Local ToDo list integration to store a copy of your on-hand wine, making it accessible to your system's AI/Voice assistant.

AI Voice Assistant with RAG | LiveKit + LLaMA Index | Intelligent document retrieval for coaching conversations

ai powered speech therapy and accent coaching app built with dreamflow powered by elevenlabs

Nexa AI is a Python-based voice assistant that streamlines daily tasks. It can open apps/websites, control volume, answer queries, perform Google searches, and generate images using speech-to-text and a decision-making model.

A voice-to-voice conversational AI built with Django, Deepgram, OpenAI, and Twilio, designed with smart time-wasting capabilities.

Enterprise-grade AI voice assistant with RAG-powered customer support, real-time phone integration, and advanced conversation management

VenomX is an advanced voice assistant for Windows, utilizing Python and AI for NLP, information retrieval, and YOLO-based object detection. It offers voice interaction, task scheduling, app management, and entertainment features. Designed to simplify tasks and demonstrate cutting-edge AI capabilities.

A 100% AWS-native AI voice calling agent that answers calls 24/7, conducts natural conversations, and captures lead information. Built with Amazon Connect, Bedrock (Claude), Transcribe, and Polly. No third-party dependencies.

A Python-based voice-controlled AI assistant for Windows using Google Gemini API, featuring speech recognition, text-to-speech, AI chat, and system automation.

A real-time voice AI system that integrates OpenAI's Realtime API, Llama3 with Twilio Voice to create intelligent voice conversations.

YuccAI is a voice assistant website for Universitas Ciputra, offering real-time answers to university-related questions via voice commands. With conversation history and topic recommendations, it simplifies access to campus information through innovative AI technology.