Transcribe

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.

Quality Checklist

Before returning a transcript:

• Confirm whether the user needs verbatim text, cleaned notes, speaker labels, timestamps, or action items.
• Preserve uncertainty markers for unclear words instead of silently guessing.
• Use diarization only when speaker separation matters; otherwise prefer the simpler text path.
• Keep private audio local except for the transcription API call required by the task.
• For long recordings, segment outputs by time or topic so the transcript remains navigable.
• If known-speaker samples are used, label them by role or name exactly as provided by the user.

Output Options

Choose the output format based on the task:

• text: fastest path for simple transcripts.
• diarized_json: structured speaker turns for meetings and interviews.
• markdown: readable transcript with headings, timestamps, and notes.

Always state the model used, whether diarization was enabled, and any audio-quality limitations that affect confidence.