According to AlphaMoat, as of 2026-09, 阿里云百炼-视频转文字 has 1,848 downloads and 1 stars — ranked #4,541 of 5,078 AI skills overall, and #308 of 362 in Content.
| Platform | Installs | Downloads | Stars | Comments |
|---|---|---|---|---|
| SkillHub ↗ | 121 | 1.8K | 1 | — |
Platforms count differently and update at different times.
The tool uses ffmpeg to extract audio, uploads it to temporary Alibaba Cloud OSS storage, and sends it to Alibaba Bailian speech recognition. DashScope and OSS credentials are required. Confirm that the media may be processed by cloud services before upload; store credentials securely and keep them out of public files and logs. The documented limit is 500 MB per video, and transcription targets Mandarin Chinese.
Profile published 2026-10-29
Generated from the skill’s documentation as examples; not results of actual runs.
The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.
| Month | Downloads | MoM | Stars |
|---|---|---|---|
| 2026-09 | 1.8K | — | 1 |
| 2026-08 | 1.3K | +23.6% | 1 |
| 2026-07 | 1.0K | +45.3% | 1 |
| 2026-06 | 708 | +38.0% | 1 |
| 2026-05 | 513 | — | - |
| 2026-03 | 182 | — | - |
The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.
--- name: aliyun-video2text description: 将本地视频文件的语音提取并转换为文字文案。当用户提到"视频转文案"、"提取视频文案"、"视频语音转文字"、"短视频文案提取"、"视频脚本提取"、"语音转写"时使用此技能。 --- # 阿里百炼视频转文案 Skill 将本地视频文件的语音提取并转换为文字文案。 ## 触发关键词
当用户提到以下关键词时,使用此技能:
- 视频转文案
- 提取视频文案
- 视频语音转文字
- 短视频文案提取
- 视频脚本提取
- 语音转写
## 功能
- 提取本地视频的音频
- 上传到阿里云 OSS(临时存储)
- 调用阿里百炼 Paraformer-v2 语音识别 API 转写
- 返回文案文本
## 限制
- 支持格式:mp4, avi, mov, mkv, flv, wmv
- 音频格式:mp3, wav, m4a, pcm
- 最大视频大小:500MB
- 最大视频时长:无限制(服务端处理)
- 转写语言:中文普通话
## 前置要求
### 1. 安装 ffmpeg
**Windows:**
```bash
# 使用 winget
winget install ffmpeg
# 或使用 chocolatey
choco install ffmpeg
```
**macOS:**
```bash
brew install ffmpeg
```
**Linux:**
```bash
sudo apt install ffmpeg # Ubuntu/Debian
sudo yum install ffmpeg # CentOS
```
### 2. 配置凭证
需要在环境变量或 `.env` 文件中配置:
```bash
# 阿里云 DashScope API Key(必填)
DASHSCOPE_API_KEY=your-dashscope-api-key
# 阿里云 OSS 配置(必填)
ALIYUN_ACCESS_KEY_ID=your-access-key-id
ALIYUN_ACCESS_KEY_SECRET=your-access-key-secret
ALIYUN_OSS_BUCKET=your-bucket-name
ALIYUN_OSS_ENDPOINT=oss-cn-beijing.aliyuncs.com
```
## 使用方式
### 提取单个视频文案
```bash
python3 scripts/video2text.py '{"video": "/path/to/video.mp4"}'
```
### 批量提取多个视频文案
```bash
python3 scripts/video2text.py '{"videos": ["/path/video1.mp4", "/path/video2.mp4"]}'
```
### 指定输出目录
```bash
python3 scripts/video2text.py '{"video": "/path/to/video.mp4", "output_dir": "/path/to/output"}'
```
## 输出格式
输出为 **JSONL**(每行一个 JSON),支持流式读取:
### 单个视频结果行
```json
{"type": "video_result", "index": 0, "video_path": "/path/to/video.mp4", "status": "completed", "text": "视频文案内容...", "duration": 65000}
```
### 汇总行
```json
{"type": "summary", "status": "completed", "total": 3, "completed": 2, "failed": 1}
```
## 工作流程
1. 校验 ffmpeg 是否可用
2. 使用 ffmpeg 从视频提取音频(转换为 mp3)
3. 上传音频到阿里云 OSS(生成临时 URL)
4. 调用阿里百炼转写 API 创建转写任务
5. 轮询任务状态,获取转写结果
6. 输出文案文本
## 错误处理
- ffmpeg 不可用:提示安装
- 凭证配置缺失:提示配置
- OSS 上传失败:输出错误信息
- 转写失败:输出错误信息,继续处理下一个文件
Detects and removes AI writing traces so text reads more like a person wrote it.
A writing-editor skill that finds the usual marks of AI-generated text and rewrites them into more natural prose without losing the meaning.
A Chinese copy-editing skill that spots and removes the traces of AI-generated text.
wechat-search finds popular WeChat articles and organizes results by relevance, popularity and recency.
Extracts titles, descriptions, and spoken scripts from public short-video share links, with rewritten versions.
humanizer guides natural expression and style editing for Chinese and English text.
Writes web-novel chapters into files and replies in chat with summaries and pointers only.
Bundle a set of marketing playbooks into one skill and route each request to the module that fits.
Data month: 2026-09 · Downloads, stars and installs are aggregated monthly from public skill registries (ClawHub, SkillHub). See methodology.