Voice Activity Detector (VAD) : low-latency, high-performance and lightweight

Self hosted, real-time digital human agent platform. Build voice-first AI agents with WebRTC, persona memory, tools, RAG, and optional digital-human video.

A PBX written by rust

One-stop handbook for building, deploying, and understanding LLM agents with 60+ skeletons, tutorials, ecosystem guides, and evaluation tools.

Official Python SDK for Deepgram.

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.

My AI Stand. Realtime by day, rewriting itself by night. Summon my AI superpower.

Official JavaScript SDK for Deepgram.

Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

🎭 Open-source AI avatar platform — upload a photo, clone a voice, talk to any face in real time. Lip-sync video, voice cloning, WebSocket streaming. Powered by Claude, Whisper & MuseTalk.

A SIP/WebRTC voice agent

Self-hosted AI voice agent

Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 1650 and edge robotics with zero-copy inference. (Apache 2.0)

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

AgentCall lets AI Agents join meetings with voice, video & screen-share to build together. Supports Google Meet, Teams, Zoom (Beta)

Open-source voice agent OS. Rust runtime, AI-driven builder, sub second latency. Self-host everything.

Official Go SDK for Deepgram.

Voice Prompts, GPT-4o prompts, Voice Agent Prompts, ChatGPT Prompts, HumeAI Prompts

Turn any SIP call into a realtime AI voice agent (OpenAI Realtime / Deepgram/Gemini Live/xAI Grok Voice)

FastAPI + MLX offline-first voice agent with <1s latency. Minimal UI