メニュー
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.
デフォルトでは、最初にソースを確認する Prompt が選択されています。直接コマンドに切り替えるか、ローカルコピーをダウンロードすることもできます。
インストールを決める前に、SKILL.md と SkillsMP に表示されている付属ファイルをお読みください。
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
直接コマンドでは確認用 Prompt が省略されます。実行前にソースを確認してください。
npx skills add https://github.com/metric-space-ai/ctox --skill transcribeコマンドは1行のまま表示されます。コピー前に横へスクロールして全体を確認してください。
ローカルで確認しますか？SkillsMP が現在取得できるファイルをダウンロードできます。
Authorized deployment readiness and go-live security audit (penetration testing, pentest, security audit, verified Python exploits) for software projects, running apps, and CTOX-created Business OS apps. Use as the final app go-live gate to assess release readiness, validate scanner and browser evidence, verify authorization boundaries, demonstrate release blockers with executed Python proofs, and produce auditable reports through one Rust CLI for Pi Code and CTOX.
Triage one inbound customer e-mail for the Decision Hub and write the proposal back through the kundenpipeline.triage.write command. Use when a CTOX queue task carries suggested_skill decision-hub-triage, so the owner receives a ready-to-approve reply draft plus a delegable task instead of raw mail — never send mail and never start the work yourself.
Durable, evidence-bound systematic research. Use for scientific or technical source discovery, literature reviews, datasets, research libraries, living Knowledge, and cited reports. The workflow mines seed papers and datasets, follows backward references and forward citations breadth-first, verifies canonical originals, persists every discovery decision, and stops only after two orthogonal rounds add no eligible source.
SOC 職業分類に基づく
SKILL.md を表示中
| 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. |
| cluster | content |
Transcribe audio using OpenAI, with optional speaker diarization when requested. Prefer the bundled CLI for deterministic, repeatable runs.
OPENAI_API_KEY is set. If missing, ask the user to set it locally (do not ask them to paste the key).transcribe_diarize.py CLI with sensible defaults (fast text transcription).output/transcribe/ when working in this repo.gpt-4o-mini-transcribe with --response-format text for fast transcription.--model gpt-4o-transcribe-diarize --response-format diarized_json.--chunking-strategy auto.gpt-4o-transcribe-diarize.output/transcribe/<job-id>/ for evaluation runs.--out-dir for multiple files to avoid overwriting.Prefer uv for dependency management.
uv pip install openai
If uv is unavailable:
python3 -m pip install openai
OPENAI_API_KEY must be set for live API calls.export CODEX_HOME="${CODEX_HOME:-$HOME/.codex}"
export TRANSCRIBE_CLI="$CODEX_HOME/skills/transcribe/scripts/transcribe_diarize.py"
User-scoped skills install under $CODEX_HOME/skills (default: ~/.codex/skills).
Single file (fast text default):
python3 "$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
references/api.md: supported formats, limits, response formats, and known-speaker notes.