voiceloop: the fastest voice agent loop in the browser is now open source

说明与用途

voiceloop 是一款开源 JavaScript 库，提供快速（862 ms 中位数）且可中断的浏览器语音代理循环，具备回声过滤和本地处理，优于现有堆栈。

问题

Building a low‑latency, interruptible voice agent in the browser was difficult due to competing open frameworks that either cut off the user’s voice or required cloud APIs.

结果

voiceloop achieves 862 ms median latency with 1067 ms p95, outperforms OpenAI Realtime and Pipecat, and eliminates self‑interruption and echo issues while remaining fully local and open source.

工作流

• 1. Install the library via npm: npm i @todoforai/voiceloop
• 2. Create a VoiceAgent instance with desired LLM endpoint, model, persona, and event handler
• 3. Call unlockAudio() on user interaction to enable microphone
• 4. Start the agent with agent.start()
• 5. Handle assistant events to render text or other UI updates

证据

voiceloop with Deepgram Flux + ElevenLabs flash is the fastest configuration we measured, at 862ms median — and its p95 (1067ms) is the tightest in the table by a wide margin.

来源

voiceloop cut itself zero times and ran echo‑coupled turns at 930ms — parity with clean.

来源