Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add joonlab/joonlab-claudecode-setting-for-share --skill elevenlabs-sttgit clone --depth 1 https://github.com/joonlab/joonlab-claudecode-setting-for-shareWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/elevenlabs-stt)<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/elevenlabs-stt"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/elevenlabs-stt/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/joonlab/joonlab-claudecode-setting-for-share/elevenlabs-stt"><img src="https://agentmods.dev/badge/skills/joonlab/joonlab-claudecode-setting-for-share/elevenlabs-stt.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.03405 |
| Opus 5 | $0.00000 | $0.01702 |
| Sonnet 5 | $0.00000 | $0.00681 |
| Haiku 4.5 | $0.00000 | $0.00341 |
Grade A, and why
elevenlabs-stt scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 183 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ElevenLabs Speech-to-Text (Scribe) + 맥락 교정
오디오/비디오를 텍스트로 변환하고, 원본 전사가 끝나면 자동으로 교정 단계가 뒤에서 돌아간다. STT는 소리만 듣기 때문에 고유명사·기술용어·동음이의어를 자주 틀린다(예: "우리회사"→"이나원(오인식 예)"). 이 스킬은 사용자의 memory·프로젝트·노트 맥락을 동적으로 끌어와 그런 오류를 잡아, 검수 없이 그대로 쓸 수 있는 전사본을 만든다.
파이프라인 개요
오디오 ──▶ [1] 전사(transcribe.py) ──▶ <name>.raw.txt (API 원본, 무손실 보존)
│ (+ keyterms 업스트림 바이어싱)
▼
[2] 맥락 라우팅(context-hints) ──▶ 관련 memory/project/노트 파일 선별
▼
[3] 교정 서브에이전트(Claude) ──▶ <name>.txt (교정본, 1차 산출물)
│ (correction-guide + 맥락 + 용어집) <name>.corrections.md (변경 로그)
▼
[4] 안전망(glossary-apply + verify) ──▶ 알려진 오류 강제 + 구조 무결성 검증
▼
[5] 학습(glossary-add) ──▶ 반복 확인된 매핑을 용어집에 누적
▼
[6] 사용자 보고
교정은 기본으로 켜져 있다. 사용자가 "교정 빼고 전사만"이라고 하면 [1]만 실행한다.
전제 조건
- 환경 변수
ELEVENLABS_API_KEY설정됨 - 지원 형식: mp3, wav, m4a, mp4, webm, flac, ogg 등 / 최대 3GB
- 교정 서브에이전트는
references/correction-guide.md와assets/glossary.json을 읽는다
[1] 전사
원본 API 출력을 <name>.raw.txt로 보존한다(교정본과 분리해 나중에 대조·검증 가능하게). --suffix raw가 이걸 담당한다.
python3 ~/.claude/skills/elevenlabs-stt/scripts/transcribe.py "<파일>" --suffix raw [옵션]
정확도 향상 — keyterms 업스트림 바이어싱(권장): 용어집의 정답 표기를 미리 API에 주입하면 오인식을 원천에서 줄인다("이나원(오인식 예)"이 애초에 안 나오게). 전사 전에 keyterms 파일을 만들어 넘긴다:
# 사용자가 도메인 힌트를 줬으면 --domains 로 좁히고, 없으면 전체 canonical 사용
python3 ~/.claude/skills/elevenlabs-stt/scripts/postprocess.py keyterms \
[--domains "사내교육"] [--extra "추가용어1,추가용어2"] \
--out /tmp/keyterms.txt
python3 ~/.claude/skills/elevenlabs-stt/scripts/transcribe.py "<파일>" --suffix raw \
--keyterms-file /tmp/keyterms.txt --language ko
- keyterms 사용 시 +20% 과금이 붙는다. 비용에 민감하거나 사용자가 "keyterms 빼줘"라고 하면 생략한다(사후 교정이 상당수 잡아준다).
- 화자가 여럿이면
--diarize --num-speakers <N>으로 화자 분리 정확도를 높인다. - 결정적 출력이 필요하면
--temperature 0.
전사 옵션(언어/화자분리/SRT 등)은 아래 "옵션" 절 참고. 이 단계가 끝나면 <name>.raw.txt(+옵션 .srt)가 생긴다.
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 183 lines · 0 tokens per session scan A f9d27dd7db89
elevenlabs-stt is a skill published in the GitHub repository joonlab/joonlab-claudecode-setting-for-share (10 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,405 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…