Curated

Chapter 36 of 44

Transcribe

Transcribe audio files to text with optional diarization and known-speaker hints.

1 minute · 238 words · 9 sections

Audio Transcribe

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

Workflow

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).
Run the bundled transcribe_diarize.py CLI with sensible defaults (fast text transcription).
Validate the output: transcription quality, speaker labels, and segment boundaries; iterate with a single targeted change if needed.
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.

Install this repository

$ npx skills add openai/skills

Skills install per repository, not per chapter — the CLI has no documented per-skill form, so we do not print one.

About this skill

Trigger

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.

The verbatim description from this skill’s front matter — the string an agent matches on to decide whether to load it.

Colophon for this issue

Colophon

How this issue was made

Source

github.com/openai/skills, branch main, last pushed 14 July 2026.

Licence

Discovery

44 chapters found by walking the repository tree for SKILL.md, not by matching a directory convention. 2 distinct layouts observed: skills/.curated/*/SKILL.md, skills/.system/*/SKILL.md.

Issue colours

Resolved from a curated brand profile — hue 170°, chroma 0.124. Two accent tones are generated per issue and each is proven against its own ground before it ships: a single accent that passes AA on both light and dark paper is arithmetically impossible.

Heading repairs

1 repair applied to this chapter so the document has one h1 and no skipped levels:

Shifted “9 headings” from h1 to h2 so the chapter title is the only h1.

Spec compliance

Every chapter satisfies the Agent Skills specification’s frontmatter rules.

Images

Images inside a chapter come from the upstream repository. Where the author gave no alternative text we mark the image decorative rather than inventing a description — a plausible caption we made up is worse than none for the reader who depends on it.

Signal

Install counts come from skills.sh. They measure downloads, not quality, and an unranked repository is not an unread one.

Agent surfaces

The whole issue is available as one markdown document at /openai/skills.md, and each chapter at its own .md URL.

Publication

Set by Skills Docs from the source repository. Body text is Literata at the reader’s chosen size and measure; code is Geist Mono. Nothing on this page was written by us except this paragraph.

Audio Transcribe

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

Workflow

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).
Run the bundled transcribe_diarize.py CLI with sensible defaults (fast text transcription).
Validate the output: transcription quality, speaker labels, and segment boundaries; iterate with a single targeted change if needed.
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.

Transcribe

Audio Transcribe

Workflow

Decision rules

Output conventions

Dependencies (install if missing)

Environment

Skill path (set once)

CLI quick start

Reference map

About this skill

Trigger

Colophon

Transcribe

Audio Transcribe

Workflow

Decision rules

Output conventions

Dependencies (install if missing)

Environment

Skill path (set once)

CLI quick start

Reference map

Appendix 36.1–36.5

ReferencesMarkdown · 1 file

ScriptsPython · 1 file

Assets2 files

Also bundled2 files

About this skill

Trigger

Colophon

Appendix 36.1–36.5

ReferencesMarkdown · 1 file

ScriptsPython · 1 file

Assets2 files

Also bundled2 files