Menu
音视频转文字技能，使用 Whisper 进行语音识别。支持多种音视频格式，可输出纯文本、SRT/VTT 字幕或 JSON 格式。适用于会议记录、视频字幕生成、采访整理、播客转录等场景。
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Baseado na classificação ocupacional SOC
Auto-generated frontmatter
Perform a dual-mode deep reading of any academic paper provided as a PDF attachment or URL. Use this skill when the user requests analysis, close reading, interpretation, or summarization of a scholarly paper. Produce two reports in a single pass: Part A is a rigorous in-depth academic analysis for researchers; Part B distills the core logic and essential value for rapid comprehension.
Use this skill when users need to search academic papers, download research documents, extract citations, or gather scholarly information. Triggers include: requests to "find papers on", "search research about", "download academic articles", "get citations for", or any request involving academic databases like arXiv, PubMed, Semantic Scholar, or Google Scholar. Also use for literature reviews, bibliography generation, and research discovery. Requires OpenClawCLI installation from clawhub.ai.
Ad intelligence & app analytics assistant. Search ad creatives, analyze apps, view rankings, track downloads/revenue, and get market insights. Get your API key at https://www.admapix.com. Triggers: 找素材, 搜广告, 广告素材, 竞品分析, 广告分析, 排行榜, 下载量, 收入分析, 市场分析, 投放分析, App分析, 出海分析, search ads, find creatives, ad spy, ad analysis, app ranking, download data, revenue, market analysis, app intelligence, competitor analysis, ad distribution.
OpenClaw skill for the agent-browser CLI (Rust-based with Node.js fallback) enabling AI-friendly web automation with snapshots, refs, and structured commands.
A fast Rust-based headless browser automation CLI with Node.js fallback that enables AI agents to navigate, click, type, and snapshot pages via structured commands.
| name | audio-video-to-text |
| description | 音视频转文字技能，使用 Whisper 进行语音识别。支持多种音视频格式，可输出纯文本、SRT/VTT 字幕或 JSON 格式。适用于会议记录、视频字幕生成、采访整理、播客转录等场景。 |
本技能使用 OpenAI Whisper 模型将音频/视频文件转换为文字。支持自动语言检测和多种输出格式。
pip install openai-whisper ffmpeg-python
确保系统已安装 ffmpeg：
# Ubuntu/Debian
sudo apt-get install ffmpeg
# macOS
brew install ffmpeg
# Windows
# 从 https://ffmpeg.org/download.html 下载
python scripts/transcribe.py <输入文件> [输出文件] [选项]
# 转录 MP4 视频，输出文本
python scripts/transcribe.py meeting.mp4
# 转录音频，输出 SRT 字幕
python scripts/transcribe.py podcast.mp3 podcast.srt --output-format srt
# 指定中文和较小模型（更快）
python scripts/transcribe.py interview.wav --model tiny --language zh
# 输出带时间戳的 JSON
python scripts/transcribe.py video.mp4 result.json --output-format json
| 选项 | 说明 | 默认值 |
|---|---|---|
--model | 模型大小：tiny, base, small, medium, large | base |
--language | 语言代码：zh, en, ja 等 | 自动检测 |
--output-format | 输出格式：txt, srt, vtt, json | txt |
--device | 运行设备：cpu, cuda | cpu |
--keep-audio | 保留临时音频文件 | false |
| 模型 | 大小 | 速度 | 精度 | 适用场景 |
|---|---|---|---|---|
| tiny | 39M | 最快 | 一般 | 快速测试、短音频 |
| base | 74M | 快 | 良好 | 日常使用 |
| small | 244M | 中等 | 较好 | 正式场合 |
| medium | 769M | 慢 | 很好 | 高精度需求 |
| large | 1550M | 最慢 | 最佳 | 专业转录 |
这是转录的完整文本内容，适合阅读和编辑。
1
00:00:01,000 --> 00:00:04,000
这是第一句字幕。
2
00:00:04,500 --> 00:00:07,000
这是第二句字幕。
WEBVTT
00:00:01.000 --> 00:00:04.000
这是第一句字幕。
00:00:04.500 --> 00:00:07.000
这是第二句字幕。
包含分段、时间戳、置信度等完整信息，适合程序处理。
音频： MP3, WAV, FLAC, OGG, M4A, AAC
视频： MP4, AVI, MOV, MKV, WEBM, FLV
--device cudascripts/transcribe.py - 主转录脚本