Original Summary

Hi HN,<p>I built Connecting Captions, a live captioning and translation overlay for macOS that runs entirely on-device. Nothing goes over the network: no API calls, no audio leaving your machine, and it keeps working offline.<p>I wanted live translation I could use in meetings and conversations without worrying about connectivity, latency spikes, or sending sensitive audio to a third party.<p>The technically interesting part is a low-latency, self-correcting pipeline for speech-to-text and translation. It has two modes:<p>Sentence mode: buffers until a sentence boundary, then translates with full context. It’s more accurate, especially between languages with different word order. Streaming mode: translates word by word as speech arrives, trading grammatical accuracy for minimal delay.<p>Current state:<p>Platform: macOS Models: Whisper Latency: ~200 ms Languages: 25<p>Code: <a href="https:&#x2F;&#x2F;github.com&#x2F;chrisswimlee&#x2F;connectingCaptions" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;chrisswimlee&#x2F;connectingCaptions</a><p>I’d love feedback, especially on the self-correction approach and which use cases matter most to people.

  • 情报分类：技术学习与提效
  • 分类依据：内容涉及技术、AI、软件工具或工程实践
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/10/18 15:41:31