mcpField
T
transcribe

transcribe

github.com/openaiCreative & media28.4k3.9k installsUpdated 18w ago
Repository

About transcribe

transcribe is a skill for transcribing audio through OpenAI, with optional speaker diarization. Its bundled CLI supports repeatable runs and text or JSON output formats.

Key features

  1. 01Transcribe audio with OpenAI
  2. 02Choose text or JSON output
  3. 03Label speakers with diarization
  4. 04Match known speaker references
  5. 05Process multiple files with output directories

Use cases

  1. 01Creating a text transcript from a recording
  2. 02Separating speakers in an interview
  3. 03Transcribing several audio files
  4. 04Saving diarized meeting output

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/openai/skills --skill transcribe

After installing, type/transcribein Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

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

Details

From the project README

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.

Comments

Markdown supported