transcribe
Transcribe audio to text with optional speaker diarization via OpenAI.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for transcribe, derived from its capabilities.
AIVSS 5.3 · Medium
View MAESTRO 7-layer threat model →Overview
An Agent Skill (author openai) that transcribes audio/video to text using OpenAI, with optional diarization and known-speaker hints. It runs a bundled CLI for deterministic runs and requires OPENAI_API_KEY; it reads audio files and emits text/json/diarized output.
Key features
- OpenAI-powered transcription
- Optional speaker diarization
- Deterministic bundled CLI
Use cases
- Transcribing interviews and meetings
- Labeling speakers in recordings