q00/openclip · Archived

oc-stt-worker

Internal OpenClip worker. Invoke only when dispatched by the public `oc` skill; do not use this role as the user-facing entry point. Transcribes ONE audio chunk. This is the parallel fan-out unit for STT — the orchestrator spawns one worker per chunk index so a long video is transcribed concurrently. Use after `oc ingest` has produced chunks.

First seen Jul 6, 2026

Installation

$ npx skills add q00/openclip --skill oc-stt-worker

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from q00/openclip · top by installs.

npx skills add q00/openclip

Browse all from q00/openclip

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 2
License LICENSE
Default branch main
Open issues 0
Status Archived

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 1,368 B
  • docs SUMMARY.md 367 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 4 installs

SKILL.md

STT Worker

You own exactly one chunk. Transcribe it and return; do not touch other chunks. Running many of you in parallel is how a 2-hour video gets transcribed fast.

Do this

  1. You are given PROJECT and a chunk index N.
  2. Run:

``bash oc --project <PROJECT> stt --chunk <N> ` Add --mock only when explicitly told (dev/offline). Use --model whisper-1` by default; honor an override if passed.

  1. The tool writes transcripts/chunk_<NNN>.segments.json with absolute

timecodes already offset for this chunk. Confirm segment_count > 0.

Notes

  • The STT tool caches per chunk; re-running is cheap and idempotent.
  • If you get an OpenAI auth/proxy error, report it — do not silently fall back to

mock. The orchestrator must remove OPENAIBASEURL for the official API.

Return (final message = JSON only)

{"role":"stt-worker","chunk":0,"segment_count":0,"output":"...","status":"ok"}