{
  "id": 18222537,
  "title": "Local speech recognition: 167 MiB of downloads and the engineering trade-offs",
  "url": "https://urgent.news/2026/11/05/local-speech-recognition-167-mib-of-downloads-and-the-engineering",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-05T01:30:07.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/di_dev_1024/local-speech-recognition-167-mib-of-downloads-and-the-engineering-trade-offs-5om"
  },
  "original_language": "en",
  "account": "Local speech recognition in Loop requires about 167.3 MiB of ASR/VAD model downloads, or 189.3 MiB when expanded, plus a platform engine and temporary installation space. This implementation does not rely on cloud speech APIs; voice input and calls submit differently as the transcript goes to the configured Agent, and a phone sends audio to the Loop host. The article explains the boundary, resource pipeline, and engineering trade-offs behind local voice input.\n\nThe decision to use local inference instead of cloud-based options involves trade-offs. Local ASR avoids sending raw audio to a cloud service for text generation, reducing network usage and provider billing. However, transcripts still cross the boundary and may be sent to a cloud-hosted coding model for processing. The resource pipeline requires separate components such as VAD, ASR, TTS, and a platform engine, each with their own disk space and code costs.\n\nThe resources needed for local voice integration are downloaded, verified, and activated after the user requests installation. Installation involves more than just model files; it includes VAD, ASR, TTS, and a platform engine, with each component requiring its own versioning, verification, and repair processes. Resource management follows six constraints: explicit installation, versioning, verification, repairability, removal, and six constraints that manage these resources.",
  "summary": "Loop's speech recognition runs on the computer hosting its backend. The implementation does not call a cloud speech API. Voice is optional: it requires installed resources and an explicit action to start listening. The cost: about 167.3 MiB of ASR/VAD model downloads, or 189.3 MiB expanded , plus a platform engine and temporary installation space. Recognition and synthesis run on the host. This…",
  "key_points": [
    "Local speech recognition requires 167.3 MiB of ASR/VAD model downloads.",
    "Implementation avoids cloud speech APIs, processing transcripts locally.",
    "Local integration involves separate components with resource management constraints."
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}