What it does. Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings. Part of openai/skills (Skills Catalog for Codex) (openai/skills).

Install

• Codex: $skill-installer installs from this catalog ($transcribe invokes it); other agents: npx skills add openai/skills --skill transcribe.
• Raw file: curl -sL https://raw.githubusercontent.com/openai/skills/HEAD/skills/.curated/transcribe/SKILL.md

SKILL.md (verbatim)

name: "transcribe"
description: "Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings."

Audio Transcribe

Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs.

Workflow

1. Collect inputs: audio file path(s), desired response format (text/json/diarized_json), optional language hint, and any known speaker references.
2. Verify OPENAI_API_KEY is set. If missing, ask the user to set it locally (do not ask them to paste the key).
3. Run the bundled transcribe_diarize.py CLI with sensible defaults (fast text transcription).
4. Validate the output: transcription quality, speaker labels, and segment boundaries; iterate with a single targeted change if needed.
5. Save outputs under output/transcribe/ when working in this repo.

Decision rules

• Default to gpt-4o-mini-transcribe with --response-format text for fast transcription.
• If the user wants speaker labels or diarization, use --model gpt-4o-transcribe-diarize --response-format diarized_json.
• If audio is longer than ~30 seconds, keep --chunking-strategy auto.
• Prompting is not supported for gpt-4o-transcribe-diarize.

Output conventions

• Use output/transcribe/<job-id>/ for evaluation runs.
• Use --out-dir for multiple files to avoid overwriting.

Dependencies (install if missing)

Prefer uv for dependency management.

uv pip install openai

If uv is unavailable:

python3 -m pip install openai

Environment

• OPENAI_API_KEY must be set for live API calls.
• If the key is missing, instruct the user to create one in the OpenAI platform UI and export it in their shell.
• Never ask the user to paste the full key in chat.

Skill path (set once)

export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export TRANSCRIBE_CLI="$CODEX_HOME/skills/transcribe/scripts/transcribe_diarize.py"

User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).

CLI quick start

Single file (fast text default):

python3 "$TRANSCRIBE_CLI" \
  path/to/audio.wav \
  --out transcript.txt

Diarization with known speakers (up to 4):

python3 "$TRANSCRIBE_CLI" \
  meeting.m4a \
  --model gpt-4o-transcribe-diarize \
  --known-speaker "Alice=refs/alice.wav" \
  --known-speaker "Bob=refs/bob.wav" \
  --response-format diarized_json \
  --out-dir output/transcribe/meeting

Plain text output (explicit):

python3 "$TRANSCRIBE_CLI" \
  interview.mp3 \
  --response-format text \
  --out interview.txt

Reference map

• references/api.md: supported formats, limits, response formats, and known-speaker notes.

Other files in this skill

• LICENSE.txt
• agents/openai.yaml
• assets/transcribe-small.svg
• assets/transcribe.png
• references/api.md
• scripts/transcribe_diarize.py

references/api.md (verbatim)

gpt-4o-transcribe-diarize quick reference

• Input formats: mp3, mp4, mpeg, mpga, m4a, wav, webm.
• Max file size: 25 MB per request.
• response_format options: text, json, diarized_json.
• For audio longer than ~30 seconds, pass chunking_strategy (use "auto" to split into chunks).
• Known speakers: up to 4 references via extra_body known_speaker_names + known_speaker_references (data URLs).
• Prompting is not supported for gpt-4o-transcribe-diarize.

Back to openai/skills (Skills Catalog for Codex) or Agent skills.