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. Parse the diarized_json output (or other JSON output) with json.loads and validate expected fields before trusting transcription quality, speaker labels, and segment boundaries. If parsing or validation fails, stop and retry with one targeted parameter change.
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.
• If a named model errors or is deprecated, check references/api.md and the provider's current model list rather than failing.

Output conventions

• Use output/transcribe/<job-id>/ for evaluation runs.
• Avoid overwriting existing output files. If the selected --out or --out-dir already exists with content, do not overwrite; ask for an explicit overwrite confirmation or a new target before writing.
• 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. Read it when hitting format, size-limit, or response-format errors.