菜单
Transcribe local audio files with the OpenAI Audio Transcriptions API without adding OpenAI dependencies to the target project.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/alexeygrigorev/.agents --skill openai-transcribe命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Reclaim disk and de-clutter git repos by finding and removing merged git worktrees, their now-merged local branches, and plain scratch dirs (`.tmp` logs/run output/caches that aren't worktrees). Use when the disk is filling up, when `git worktree list` / `git branch` are bloated with stale agent or task worktrees (`agent-*`, `tester-*`, `issue-*`), or when asked to "clean up git" / free space. Full procedure is in worktrees.md.
Create polished workflow diagrams as deterministic SVG and PNG files from JSON specifications. Use when Codex needs to visualize a process, lifecycle, state flow, branching workflow, circular loop, or ASCII diagram.
Write or rewrite prose with a pinned Claude model version (e.g. opus 4.6), keeping structure, numbers, quotes and markup byte-identical. Use whenever the user names a model version for writing, or wants a draft rewritten for voice.
基于 SOC 职业分类
正在显示 SKILL.md
| name | openai-transcribe |
| description | Transcribe local audio files with the OpenAI Audio Transcriptions API without adding OpenAI dependencies to the target project. |
| allowed-tools | Bash(python *) |
| argument-hint | ["audio-file ..."] |
Use scripts/transcribe.py to transcribe local audio through the
OpenAI Audio Transcriptions API.
The script intentionally uses only the Python standard library. It
does not add openai or any other dependency to the repository being
worked on.
The script reads the API key in this order:
OPENAI_API_KEY from the current environment.--env-file /path/to/.env, reading OPENAI_API_KEY=....--auto-env, scanning local project .env files under
/home/alexey/git and using the first file that contains
OPENAI_API_KEY.The key is never printed.
python /home/alexey/git/.agents/skills/openai-transcribe/scripts/transcribe.py \
--auto-env \
--model whisper-1 \
--language ru \
--out-dir docs/source-recordings \
docs/source-recordings/example.m4a
For whisper-1, the script requests verbose_json and writes both
the raw JSON response and a timestamped .txt file.
Files larger than the OpenAI upload limit are split with ffmpeg
before transcription, then combined back into one timestamped output.