# QwenAudio/qwen-audio-agent

A realtime voice runtime that keeps Agents talking, working, and present.  Real-time Voice Runtime for AI Agents

Repository: https://github.com/QwenAudio/qwen-audio-agent
Canonical: https://ross.abutalabs.com/products/qwen-audio-agent
Language: JavaScript
License: Apache-2.0
License Family: permissive
Topics: agent, agentic-ai, voice-agent, voice-ai, voice-chat, acp, ai-coding, claude-code, codex, developer-tools, opencode, speech-recognition, text-to-speech
Last push: 2026-08-26T18:03:41+00:00

## Health v2 (maintenance only)
Score: 79/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 98, longevity 2
- inputs: {"age_days": 37, "days_push": 7, "days_rel": 13, "gap_med": 0.0, "n_releases_24m": 27}
- flags: young
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2264, forks 191 (observed 2026-08-28T04:06:32.521347+00:00)

## What it is
A realtime voice runtime and frontend for AI coding agents like Claude Code, Codex, and Qwen Code, letting agents talk, listen, and report progress while working. It ships as an npm package with a desktop app and TUI, including speech recognition, text-to-speech, wake word, and memory features.

## Use cases
- talk to my coding agent by voice
- realtime voice interface for claude code
- voice chat with ai agent while it works
- add speech recognition and tts to an agent
- voice wake word assistant for developer tools
- hear agent progress updates hands-free

## When to choose
- you use Claude Code, Codex, Qwen Code, or similar agents and want voice interaction
- you want an agent that stays present and reports progress while running tasks
- you want a cross-platform desktop or terminal voice frontend

## When to avoid
- you need a backend voice pipeline SDK to embed in your own product
- you need text-only agent interaction
- you need production telephony or call-center voice features

## Facets
- artifact type: application
- maturity: active
- function: speech-recognition, tts, agent-framework, chat-interface, audio-processing, cli
- domain: speech-processing, large-language-models, developer-tools
- platform: cross-platform, windows
- tags: voice-agent, realtime-voice, voice-frontend, claude-code, codex, wake-word, tui, desktop-app, acp, ai-agents, voice, nodejs, desktop, macos, linux

## Member repositories
- QwenAudio/qwen-audio-agent (main) score 79

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:32.521347+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:42:25.880850+00:00, confidence not recorded.
  - readme: https://github.com/QwenAudio/qwen-audio-agent (fetched 2026-08-28T04:06:32.521347+00:00, sha 18062f80c6be)
  - registry_npm: https://registry.npmjs.org/qwen-audio-agent (fetched 2026-08-29T10:23:07.923927+00:00, sha dcdb25ef5c40)
- Data as of 2026-08-30T08:39:29.467469+00:00.