llblab/groq-stt
groq-stt/SKILL.md
Transcribe audio files using Groq API (Whisper).
$ install --global
skillsauthnpx skillsauth add llblab/skills groq-sttInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Jun 12, 2026, 7:33 AM46.4s5 files scanned
SKILL.md
- name:
- groq-stt
- description:
- Transcribe audio files using Groq API (Whisper).
- version:
- 1.0.16
Groq STT Skill
Standalone direct Node.js client for Groq's Whisper transcription API. The canonical client is scripts/transcribe.mjs; scripts/transcribe.sh is the shell entrypoint wrapper. There are no curl fallbacks or JSON parser dependencies.
Usage
GROQ_API_KEY=xxx ./scripts/transcribe.sh audio.ogg [language] [model]
GROQ_API_KEY=xxx ./scripts/transcribe.sh --file audio.ogg --lang ru --model whisper-large-v3-turbo
language— optional language code; omitted means provider auto-detection.model— optional; default:whisper-large-v3-turbo.- Outputs only the transcription text.
- Fails fast when the file or
GROQ_API_KEYis missing. - Supports both positional and flag-style invocation.
CLI Options
--file,-f— audio file path.--lang,--language,-l— optional language code.--model,-m— Groq transcription model.--help,-h— usage.
Dependencies
- Node.js 18+ with built-in
fetch,FormData, andBlob. - Internet access.
Notes
- Default model:
whisper-large-v3-turbo. - Uses
response_format=textso stdout stays clean for attachment handlers. - Preserves positional invocation used by
transcribe_groq:transcribe.sh {file} {lang} {model}.
Related Skills
llblab/extra-self
development
VerifiedTrustedCommunity
High-density memetic-systems cognition mode. Use for extra self, be yourself, give me the base, foundational synthesis, first-principles compression, deep structure, memetic analysis, strong framing, naming, narrative architecture, ideology, culture, protocol dynamics, governance, economics, product strategy, institutional diagnosis, prompt/spec compression, or architecture-first strategic thought.
6SKILL.mdUpdated Jun 12, 2026
llblab/dev2main-release
development
VerifiedTrustedCommunity
Manage a guarded release flow that commits prepared release work on dev, opens a dev-to-main pull request with a release-focused PR summary, waits for checks, merges on success, tags, and optionally publishes an existing npm package. Use when the user asks to prepare or execute a dev→main release PR, hotfix release PR, or Dev2Main PR Summary workflow.
6SKILL.mdUpdated May 19, 2026
llblab/bits-ui
tools
VerifiedTrustedCommunity
Build, refactor, review, or debug Svelte 5 components that use Bits UI primitives. Use when working with bits-ui dialogs, popovers, dropdowns, comboboxes, selects, tabs, date/time controls, menus, tooltips, portals, render delegation, or Bits UI type helpers.
6SKILL.mdUpdated May 15, 2026
llblab/re-review
development
VerifiedTrustedCommunity
Evidence-grounded review for code, diffs, PRs, documents, plans, specs, and architecture. Use for evidence review, review, code review, quick review, sanity check, quality check, architecture review, production readiness, security review, scaling review, document review, evaluate, or check.
6SKILL.mdUpdated May 8, 2026