Skip to content
Back to skills

Openclaw Skill Whisper Stt

ASecurity

语音转文字 - 使用OpenAI Whisper将音频文件识别为文字

  • 14 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 7, 2026
ai-agentspython

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 7, 2026

npx -y skills add modbender/skill-library-mcp --skill openclaw-skill-whisper-stt --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Openclaw Skill Whisper Stt?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Openclaw Skill Whisper Stt
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/modbender-openclaw-skill-whisper-stt/badge)](https://www.skillsdirectory.com/skills/modbender-openclaw-skill-whisper-stt)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: whisper-stt
description: 语音转文字 - 使用OpenAI Whisper将音频文件识别为文字
---

# Whisper 语音转文字技能

将音频/语音文件识别并转换为文字。

## 使用方式

### 自动处理(推荐)

当用户发送语音/音频文件时,自动:
1. 识别语音内容
2. 转换为文字
3. 发送文字到飞书

### 手动命令

用户发送音频文件后,技能自动处理。

## 支持格式

- MP3, WAV, M4A, OGG, FLAC, WebM
- 任何音频格式(FFmpeg支持即可)

## 模型选择

| 模型 | 大小 | 速度 | 精度 |
|------|------|------|------|
| tiny | ~1GB | 最快 | 基础 |
| base | ~1GB | 快 | 一般 |
| small | ~2GB | 中等 | 较好 |
| medium | ~5GB | 较慢 | 很好 |
| large | ~10GB | 最慢 | 最佳 |
| turbo | ~6GB | 快 | 接近large |

## 技术实现

```python
import whisper

# 加载模型(首次使用会下载)
model = whisper.load_model("base")  # 可选: tiny/base/small/medium/large/turbo

# 识别语音
result = model.transcribe("audio.mp3")

# 输出文字
print(result["text"])
```

## 依赖

- Python 3.8+
- PyTorch
- openai-whisper
- ffmpeg

## 注意事项

1. 首次使用会下载模型(1-10GB)
2. 大模型需要较多内存
3. 中文识别效果很好

Files in this skill

  • README-CN.md2.8 KB
  • README.md3.3 KB
  • SKILL.md1.3 KB
  • transcribe.py2.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…