audio-transcription

Name: audio-transcription
Author: matthewkeilbot

Transcribe inbound audio clips to text using local Whisper (faster-whisper). Use when the user sends voice notes/audio files and asks what was said, asks for transcript/summary/action items, or asks t

by matthewkeilbot(0) 0 installs

Free

Free account. Installing gives you the manifest plus copy-paste snippets.

See reviews

About

Imported from matthewkeilbot/silicon-simian (skills/audio-transcription/SKILL.md). Install upstream with npx skills add matthewkeilbot/silicon-simian --skill audio-transcription. Copyright stays with the author.

Audio Transcription (Local, small.en)

Use local transcription by default with small.en.

Default command

python3 skills/audio-transcription/scripts/transcribe_local.py \
  --input "<audio-path>" \
  --model small.en

Fast/lower-resource fallback

python3 skills/audio-transcription/scripts/transcribe_local.py \
  --input "<audio-path>" \
  --model base.en

What to return to user

Transcript (verbatim best-effort)
Short summary (2-4 bullets)
Action items/questions extracted from transcript
If confidence seems low, say so clearly

Notes

First run downloads model weights (~500MB for small.en).
Keep transcripts concise in chat; offer full dump on request.
Treat audio content as sensitive by default; do not share externally.

Use it

Copy one of these into your project. Installing also returns the manifest and these snippets.

# after Install: the listing is in your workspace's routing pool - a plan picks it for its slot
curl -s -X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'

Manifest

An Open Capability Manifest: the router reads it to know what this does, what it costs and when to pick it.

matthewkeilbot-silicon-simian-audio-transcription.ocm.jsonjson

{
  "ocm": "1",
  "id": "matthewkeilbot-silicon-simian-audio-transcription",
  "kind": "skill",
  "name": "audio-transcription",
  "description": "Transcribe inbound audio clips to text using local Whisper (faster-whisper). Use when the user sends voice notes/audio files and asks what was said, asks for transcript/summary/action items, or asks to process audio privately on-host. Default model is small.en for better English accuracy on constrained hosts.",
  "publisher": "matthewkeilbot",
  "version": "1.0.0",
  "capabilities": {
    "domains": [
      "general"
    ],
    "tags": [
      "skill-md",
      "github"
    ],
    "languages": [
      "en"
    ]
  },
  "quality_prior": 0.6,
  "examples": [
    "Transcribe inbound audio clips to text using local Whisper (faster-whisper). Use when the user sends voice notes/audio files and asks what was said, asks for transcript/summary/action items, or asks to process audio privately on-host. Default model is small.en for better English accuracy on constrained hosts."
  ],
  "primary": false,
  "metadata": {
    "source": {
      "provider": "github",
      "repository": "https://github.com/matthewkeilbot/silicon-simian",
      "path": "skills/audio-transcription/SKILL.md",
      "ref": "26b55f16f939b8813dfe8a0cfaa54f8bc0f0aac7",
      "url": "https://github.com/matthewkeilbot/silicon-simian/blob/26b55f16f939b8813dfe8a0cfaa54f8bc0f0aac7/skills/audio-transcription/SKILL.md",
      "key": "matthewkeilbot/silicon-simian/skills/audio-transcription/SKILL.md"
    }
  },
  "instructions": "# Audio Transcription (Local, small.en)\n\nUse local transcription by default with `small.en`.\n\n## Default command\n\n```bash\npython3 skills/audio-transcription/scripts/transcribe_local.py \\\n  --input \"<audio-path>\" \\\n  --model small.en\n```\n\n## Fast/lower-resource fallback\n\n```bash\npython3 skills/audio-transcription/scripts/transcribe_local.py \\\n  --input \"<audio-path>\" \\\n  --model base.en\n```\n\n## What to return to user\n\n1. Transcript (verbatim best-effort)\n2. Short summary (2-4 bullets)\n3. Action items/questions extracted from transcript\n4. If confidence seems low, say so clearly\n\n## Notes\n\n- Fir",
  "cost": {
    "context_tokens": 197
  }
}

Fetch it by URL: GET /api/v1/registry/matthewkeilbot-silicon-simian-audio-transcription/manifest?version=1.0.0