Original Summary

nanosamur.ai is a speech-to-tech platform that supports different models for realtime, semi-realtime, and batch transcription and provides a unified stack for robust speech processing, agentic workflows, and webhooks.<p>You can run it locally on your computer via electron app + docker compose, but you can take the same stack and run it in cloud&#x2F;k8s and&#x2F;or on prem as it is built with scale in mind (it also has an observability stack built in). So in that sense it is more like Ollama + Ollama Cloud :)<p>Currently it supports whisper, qwen asr, nemotron asr and parakeet tdt and I am adding other models. I am also adding Kserve+Triton integration for the batch transcriptions so as the MLOps can be abstracted away.<p>Last couple of years I have been consulting for some organizations that work with sensitive data and have to keep them in air gapped environments and based on those experiences I built and open-sourced nanosamur.ai<p>The easiest place to start is the main repo: <a href="https:&#x2F;&#x2F;github.com&#x2F;nanosamurai&#x2F;nanosamurai" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;nanosamurai&#x2F;nanosamurai</a><p>It is a docker compose starter setup, there are couple of services it uses, all are linked in the documentation; I used python for the voice ai services (see the xamurai monorepo) and java &#x2F; clojure &#x2F; clojurescript for the UI&#x2F;BFF and some other services (yes, it is pg&#x27;s fault i love lisps).<p>Appreciate any feedback! Esp. from people working with speech infrastructure, self hosted AI etc. Also it currently sits at 6 stars, so feel free to star the repos if you like them :)

  • 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：2026/9/21 22:17:22