qwen-audio-agent
View on GitHubA realtime voice runtime that keeps Agents talking, working, and present. Real-time Voice Runtime for AI Agents
A JavaScript runtime for real-time voice conversations with AI agents, offering WebUI, terminal, and desktop clients. It connects interchangeable voice services to backend agents such as Claude Code, Codex, and OpenCode, with parallel background tasks and session memory.
Use Cases
Build a real-time voice interface for coding agentsRun background agent tasks during voice conversationsCreate voice-controlled desktop assistantsConnect agents to mobile clients for remote accessBuild voice-enabled customer service assistantsAdd speech interaction to smart cockpits or digital humans
Built With
- Language
- JavaScript
- Frameworks
- Electron · Capacitor · WebRTC · ACP · A2A
Tags
voice agent · real-time audio · speech-to-text · text-to-speech · agent orchestration · ACP · multimodal · desktop app · WebUI · TUI · memory