Name: Aliyun Asr
Author: Jixson

According to AlphaMoat, as of 2026-09, Aliyun Asr has 3,682 downloads and 2 stars — ranked #2,934 of 5,078 AI skills overall, and #274 of 512 in Design & Media.

Installs

115

Downloads

3.7K

Stars

Overall Rank

#2,934

Top 58% overall · Top 54% in Design & Media

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	112	3.5K	2	-
SkillHub ↗	115	3.7K	2	—

Platforms count differently and update at different times.

What this skill does

This ASR skill transcribes audio without generating spoken replies and passes the transcript to the AI as a user message. Aliyun NLS credentials are required. Audio is sent to Aliyun; converted audio files may remain on disk, so review cleanup before use.

Profile published 2026-10-29

What you can do with it

Transcribe voice messages from channels such as Feishu, Telegram, or WhatsApp
Let an AI handle the request using the transcript
Review the required Aliyun NLS credential setup

When to use it

When you need to turn a voice message into text
When you want follow-up processing on the transcript

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Transcribe this voice message into text without generating a spoken reply.

Explain where the audio is sent and remind me to check cleanup of local converted files.

Monthly Trend

Downloads3.7K

Stars2

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	3.7K	—	2
2026-08	3.4K	+5.1%	2
2026-07	3.2K	+9.4%	2
2026-06	3.0K	+5.0%	2
2026-05	2.8K	—	2
2026-03	2.1K	—	2

SKILL.md (original)

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.

2.3 KB · ClawHub v1.0.10

---
name: aliyun-asr
description: "Pure Aliyun ASR skill for voice message transcription, supports multiple channels including Feishu"
metadata:
  {
    "openclaw":
      {
        "emoji": "🎙️",
        "requires": { "bins": ["python3"] },
        "install": [],

Show all (76 lines)

      },
  }
---

# 阿里云语音识别 (Aliyun ASR) 技能

**纯语音识别，无语音合成** - 这是一个专门为OpenClaw设计的轻量级阿里云语音识别技能，只做一件事：将语音消息转换为文本。

## 🎯 核心功能

- **✅ 纯ASR识别**: 只进行语音到文本的转换，**不生成任何语音回复**
- **✅ 多通道支持**: 支持飞书(Feishu)、Telegram、WhatsApp等所有OpenClaw支持的语音消息通道
- **✅ 自动集成**: 无需额外配置，语音消息自动被识别并作为文本消息处理

## ⚙️ 快速配置

### 1. 阿里云准备
- 开通 [智能语音交互(NLS)](https://nls-portal.console.aliyun.com/) 服务
- 在RAM控制台创建子用户并分配 `AliyunNLSFullAccess` 权限
- 在NLS控制台创建应用，获取 **AppKey**

### 2. 配置文件
创建配置文件 `/root/.openclaw/aliyun-asr-config.json`:

```json
{
  "access_key_id": "your-access-key-id",
  "access_key_secret": "your-access-key-secret",
  "app_key": "your-app-key",
  "region": "cn-shanghai"
}
```

### 3. 安全设置
```bash
chmod 600 /root/.openclaw/aliyun-asr-config.json
```

## 🚀 使用方法

### 自动模式（推荐）
1. 用户向任何支持的通道发送语音消息
2. OpenClaw自动调用此技能识别语音内容
3. **识别的文本作为用户消息传递给AI**
4. **AI生成纯文本回复（不是语音）**

## 🔧 技术细节

- **依赖**: `requests` (Python包)
- **支持格式**: MP3, WAV, OGG, FLAC, AMR, OPUS
- **API区域**: 默认 `cn-shanghai`（可配置）

## 🛡️ 安全与合规

- **无数据存储**: 语音数据不存储在本地
- **最小权限**: 使用RAM子账号，避免主账号密钥
- **配置分离**: 敏感信息与代码完全分离

## 💡 开发规范

此技能严格遵循以下开发准则：
1. ✅ 完全符合开源skills的配置要求
2. ✅ 完全符合当地的法律法规要求  
3. ✅ 未开发或未实现的功能，不包含在源码中
4. ✅ 本地测试代码，测试用例不包含在源码中
5. ✅ 密钥/认证隐私信息，不包含在源代码中