elumenotion/guideants/audiocpp-asr-extended
Claude Code and agent skill by elumenotion/guideants
- community
Checking that the SKILL.md file is still in the repository.
Transcription beyond the GuideAnts wrapper contract: transcribe workspace files by path (no upload, no 50 MB gateway cap), pass language hints, and sideload other qwen3-family ASR snapshots from Hugging Face through the wrapper. Use when a transcription needs a language hint, the file is large, or the user wants to try an ASR model the catalog doesn't list.
Install
npx vskill@latest install elumenotion/guideants/audiocpp-asr-extendedSKILL.md
audio.cpp extended ASR (experimental)
The GuideAnts ASR wrapper (127.0.0.1:8082) takes multipart uploads with no language control. The raw engine it spawns (127.0.0.1:18082) accepts a server-local path and a language hint — and the sandbox shares its filesystem, so any workspace file qualifies. The wrapper also loads bare model directories the catalog doesn't list (unlike the strictly-gated TTS wrapper).
Preflight
Trust its verdict over this document. open: false means no ASR model is loaded — ask the user to load one via GuideAnts Settings → Local models. Warnings tell you whether the sideload path (below) is available.
Transcribing by path (with language hint)
- No upload and no gateway size cap — the engine reads the file in place.
- The engine model id is always
qwen3-asr(fixed by the wrapper), whatever
snapshot is actually loaded.
- Input should be WAV for the raw engine; for other formats, either convert
with ffmpeg first or use the wrapper upload (POST :8082/transcribe, multipart field audio), which re-encodes to 16 kHz mono itself.
Sideloading a non-catalog ASR snapshot
The ASR wrapper's /admin/load accepts any bare directory under /models-local/asr whose leaf name matches the model_id. The engine family defaults to qwen3_asr, so only qwen3_asr-family snapshots work (other families would need the GA_ASR_ENGINE_FAMILY env at service start — a compose change, out of skill scope).
Warning — this replaces the user's loaded ASR model. Ask before doing it, and offer to restore afterwards:
Note: GuideAntsApi routing policy (lifecycle plan + apply) owns wrapper load state — a sideload can be silently undone by a later API apply (e.g. after a local-LLM switch). Treat sideloads as session-scoped experiments, not durable configuration.
Related
Speaker-labeled transcripts ("who said what") are the audiocpp-diarize skill.
Reporting
End by telling the user what worked and what was blocked, quoting the preflight/engine evidence.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingsamples/guides/Audiocpp/Skills/audiocpp-asr-extended/SKILL.md
Popularity
- 7-day trend score
- 0
Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/elumenotion/guideants/audiocpp-asr-extended)