moldable-ai/openai-transcribe
skills/openai-transcribe/SKILL.md
Transcribe local audio files with OpenAI speech-to-text through aivault capability json (no provider API key in skill runtime).
development
Updated Apr 22, 2026
$ install --global
skillsauthnpx skillsauth add moldable-ai/skills openai-transcribeInstall 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: Apr 22, 2026, 5:16 PM100.1s2 files scanned
SKILL.md
- name:
- openai-transcribe
- description:
- OpenAI API key for speech-to-text transcription
- compatibility:
- Requires `aivault` CLI and Node.js (runs via `npx tsx`).
- - name:
- OPENAI_API_KEY
- required:
- true
OpenAI Transcribe
This skill uses aivault to always keep your API keys safe.
Setup
Install aivault if it is not already available:
curl -fsSL https://aivault.moldable.sh/install.sh | sh
Store your OpenAI API key in aivault. The credential and all openai/* capabilities are auto-provisioned from the built-in registry.
aivault secrets create --name OPENAI_API_KEY --value "sk-..." --scope global
This skill uses openai/transcription.
Quick start
npx -y tsx {baseDir}/scripts/transcribe.ts /path/to/audio.m4a
Common examples
npx -y tsx {baseDir}/scripts/transcribe.ts /path/to/audio.wav
npx -y tsx {baseDir}/scripts/transcribe.ts /path/to/audio.wav --json
Notes
- Capability id is hard-coded to
openai/transcription. - Default model sent to upstream is
whisper-1. - The script uses
aivault jsonso upstream JSON is parsed/validated by aivault; without--jsonit prints just the extracted transcript text.
Related Skills
moldable-ai/firecrawl
development
VerifiedTrustedCommunity
Search, scrape, crawl, map, parse, and operate Firecrawl browser/agent workflows through aivault-backed Firecrawl API capabilities. No Firecrawl API key is read by the skill runtime.
SKILL.mdUpdated May 30, 2026
moldable-ai/trello
data-ai
VerifiedTrustedCommunity
Manage Trello boards/lists/cards via aivault-backed capabilities (no Trello key/token in skill runtime).
SKILL.mdUpdated Apr 22, 2026
moldable-ai/todoist
documentation
VerifiedTrustedCommunity
Manage Todoist tasks/projects/comments via aivault-backed capabilities (no Todoist token in skill runtime).
SKILL.mdUpdated Apr 22, 2026
moldable-ai/openai-image-gen
development
VerifiedTrustedCommunity
Generate images via OpenAI Images API through aivault (no OpenAI API key in skill runtime). Writes images plus an index.html gallery.
SKILL.mdUpdated Apr 22, 2026