voice-agents

Open source voice AI platform. Self-hosted alternative to Vapi and Retell. On Prem, BYOK across Speech to Speech or LLM/STT/TTS, with a visual workflow builder, MCP native and telephony support.

Conversational voice AI agents

Rapida is an open-source, end-to-end voice AI orchestration platform for building real-time conversational voice agents with audio streaming, STT, TTS, VAD, multi-channel integration, agent state management, and observability.

Build AI phone agents on your own computer and test every change with an AI caller. Open source, runs free with no API keys, cents per call with your own keys. Imports Dialogflow CX.

Open-source, self-hostable platform for building and operating AI phone agents.

Set of 📝 with 🔗 to help those building Voice AI agents 🎙️🤖

Build realtime voice and video agents with Google's new Gemini 2.0 (API is free for now)

Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic frameworks

A New End-to-end Framework for Evaluating Voice Agents

DialogLab is an authoring tool for configuring and running Human-AI multi-party conversations.

A self-improving loop for voice AI agents. Uses karpathy's autoresearch as foundation.

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

React components for voice agents, chat, and generative UI. LiveKit, ElevenLabs, and OrbKit in one kit. Copy the source and make it yours.

Addressee detection for voice agents: device-directed speech detection that runs before STT, so background speech, side conversations, and the agent's own TTS echo never trigger it. No wake word, model-agnostic, drop-in for LiveKit, Pipecat, ElevenLabs, Twilio, and OpenAI. The layer your VAD and turn detection are missing.

Self-hosted native-Rust runtime for real-time voice agents. Own the stack: one binary in your own VPC or air-gapped, no hosted control plane. pipecat-compatible pipeline, in-process SIP/RTP, single-process call density. Apache-2.0.

The ElevenLabs Agents SDK for TypeScript.

Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy.

The Open Source Voice Agent Platform - Build voice agents by connecting nodes in a canvas, deploy them to handle inbound and outbound phone calls, and monitor every call, latency and cost.

Open-Source CPAAS for Contact Center Teams.

The best performing voice isolator there is. Keeps the caller's voice and removes the other voices in the room before speech-to-text hears them. Open source, streaming, runs on CPU and in the browser. pip install voxlock