webrtc

React / Vanilla JS Text to Speech with highlighting the words and sentences that are being spoken using audio files, text to speech API, and web speech synthesis API

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.

ChatPlus is a progressive web app developped with React, NodeJS, Firebase and other services

A programmable Voice AI platform: SIP and WebRTC call control, multi-party mixing, recording, TTS/STT, and pluggable AI agents (ElevenLabs, VAPI, Pipecat, Deepgram) — all driven through a REST API, webhooks, and a WebSocket event stream

🗣️ Real‑time, low‑latency voice, vision, and conversational‑memory AI assistant built on LiveKit and local LLMs

Speech-to-text and keyboard input captions for OBS.

An open source chat bot architecture for voice/vision (and multimodal) assistants, local(CPU/GPU bound) and remote(I/O bound) to run.

A WebRTC-native, audio-first conversational-AI framework for Go.

The virtual secretary, Lisa, is designed to interact naturally with users through text, voice, emotion, and a real-time animated avatar.

The open-source foundation for production Voice AI. Build, scale, and own your AI calling infrastructure. Bridge legacy SIP to modern LLMs over ultra-low latency WebRTC pipelines. Zero platform fees, BYOK, and full data sovereignty.

Set of PocketBase plugins to add features

Developer tools to debug and build realtime voice agents. Supports multiple models.

Talk To AI with FastRTC enables natural, real-time voice conversations with AI using WebRTC, offering customizable voices, interfaces, and local or cloud-based API integration.

This is an encrypted Angular 21 PWA messenger application with an AI friend that can work offline and has a reactive Spring Boot 3 backend with a MongoDB to store the messages in a clean architecture. With a Kubernetes setup. Structurizr is used for C4 diagrams.

Sky LiveKit Agent Perplexica is a local, free solution integrating LiveKit with advanced internet search. It uses a local Perplexica instance with function calling to retrieve and summarise search results in natural language. Powered by Faster Whisper, Ollama (Qwen 2.5) and Kokoro-82M TTS.

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

A video call apps to enable deaf people to communicate with normal people using sign language recognition and speech-to-text