realtime

🤖 An open-source, AI agent-native research canvas application that performs real-time search with HITL (Human in The Loop) capabilities, powered by CopilotKit, Tavily and LangGraph

A Java library to use the OpenAI Api in the simplest possible way.

System audio capture + multi-provider ASR + local-first AI review workspace. Floating live captions, 12 ASR backends, 60+ languages, AI summary/chat/mindmap, Open API, MCP server, and Agent Skill.

A library for real-time voice processing in web browsers

🪐 HelixWorld: real-time interactive audio-visual world model.

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

Realtime Interview Copilot is a desktop application that assists users in crafting responses during interviews. It leverages real-time audio transcription and AI-powered response generation to provide relevant and concise answers.

A wayland overlay providing speech-to-text functionality for any application via a global push-to-talk hotkey

Nomi enable people to use computer more simply.

This repository focuses on leveraging OpenAI's Whisper model for speech recognition in Chinese (Mandarin) and Taiwanese Hokkien languages. It includes tools and scripts for data preprocessing, model training, and evaluation, tailored to improve speech recognition accuracy for these languages.

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

LLM-powered security log analyzer: detect threats & anomalies with zero regex — just declare a Pydantic schema. Real-time Telegram alerts, SIEM-ready with Elasticsearch/Kibana. Supports OpenAI, Ollama, vLLM.

Cloud AI live transcription and translation service plugin

Rev AI Python SDK

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

Node.js SDK for the Rev AI API

A simple way to add speech to text functionality to your website :microphone:

VTuber application which only requires your voice and microphone, no need for a webcam or other tracking nonsense.

Heterogeneous Edge Realtime Measurement and Execution System: A Unified Open-Source Framework for Realtime Multimodal Physiological Sensing, Edge AI, and Intervention in Closed-Loop Smart Healthcare Applications