openai-realtime

Formerly Better Chatbot. Navigator is an open-source AI workspace for agents, MCP and workflow automation.

Vui Nano — a small, context-aware text-to-speech model trained on real conversations. 219M active params (305M total), Apache 2.0, voice cloning, streaming, runs on CPU (dependency-free C build). Ships with a full real-time voice assistant: WebRTC, ASR, local LLM, OpenAI Realtime API compatible.

Opensource, on-device voice + vision layer for AI agents. Bring any model or coding agent; the whole speech loop (VAD, STT, TTS, barge-in) runs locally. An open alternative to ElevenLabs Agents, Gemini Live, and OpenAI Realtime.

Open-source MCP server for safe, stateful AI-agent phone calls with OpenAI Realtime and Twilio.

Self-hosted, API-first AI call center. Realtime voice bots answer every call, human agents take over without a drop. Full REST + SSE API with OpenAPI spec to embed in your product. FreeSWITCH + OpenAI Realtime / Qwen, one Go binary.

Open-source, self-hosted AI phone receptionist powered by OpenAI Realtime API. High-fidelity speech-to-speech voice agent. Drop-in replacement for overpriced AI receptionist SaaS.

Voice-driven multi-agent assistant — Realtime API + CLI runners + multi-channel orchestration.

AI Phone Agent: A starter kit to build AI agents that answer real phone calls and talk to customers in real time. Amazon Connect, OpenAI SIP, and the OpenAI Realtime API. Dial +1 844-593-8442 to try the demo.

Give your AI assistant a phone — OpenClaw plugin for real phone calls via Twilio + OpenAI Realtime, with in-call tools, transcripts, and call screening

Self-hosted realtime voice gateway for Hermes Agent. Keep talking while Hermes runs background tasks through local, Gemini Live, and OpenAI Realtime adapters.

Hermes Talk: realtime duplex voice for Hermes Agent. Rides your ChatGPT or X Premium subscription, no API key needed. OpenAI, Grok, Gemini. Terminal, Discord, dashboard.

FreeSWITCH module that streams live call audio to AI voice agents over WebSocket and plays their voice back — full-duplex.

Self-hosted voice gateway in Go that speaks the OpenAI Realtime (GA) WebSocket protocol and runs a cascaded ASR → LLM → TTS pipeline behind it. Keep clients unchanged while swapping speech and LLM providers at runtime

Voice rubber-duck debugging assistant: a FastAPI backend bridges the browser (WebRTC) to the OpenAI Realtime API, with server-side tools for web search, URL fetch, weather, and per-user memory.

Implementation of OpenAI's Realtime API in Unity. Easily integrate low-latency, multi-modal conversations via push-to-talk or text.

Skilly : A voice-first AI tutor that watches your screen

Voice to brain interface 🦞🎤🧠 for OpenClaw, Hermes, PI, etc

🎙️ OpenAI Realtime API with tools and webhook support

One voice agent to control all your Claude Code sessions — drive them hands-free from your browser or phone.

Open-source real-time voice AI platform — sub-450ms latency, 100+ concurrent sessions. Self-hosted alternative to OpenAI Realtime API.