transcribe

Transcribe audio files to text with optional speaker diarization and known-speaker hints. Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs. Prefer uv for dependency management. If uv is unavailable: User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills ). Single file (fast text default): Diarization with known speakers (up to 4): Plain text output (explicit): - Supports fast text transcription via gpt-4o-mini-transcribe and speaker-labeled diarization via gpt-4o-transcribe-diarize - Accepts multiple audio formats and optional known-speaker references (up to 4 speakers) to improve diarization accuracy - Outputs as plain text, JSON, or diarized JSON with configurable output directories to prevent overwrites - Requires OPENAI_API_KEY environment variable; uses bundled Python CLI for deterministic, repeatable transcription runs - Collect inputs: audio file path(s), desired response format (text/json/diarized_json), optional language hint, and any known speaker references. - Verify OPENAI_API_KEY is set. If missing, ask the user to set it locally (do not ask them to paste the key).