什么是 Plaud API？

此 Openclaw Skills 扩展提供了一个与 Plaud API 交互的全面接口，弥补了硬件录音笔与数字化开发人员工作流之间的鸿沟。它使用户能够直接从 Plaud 云服务检索高质量的 MP3 录音、带有说话人标签的转录文本以及自动生成的 AI 摘要。

通过使用内置的 Python 客户端，此技能简化了复杂的身份验证和响应解析，从而将语音数据无缝集成到您的本地环境中。它专为需要管理其语音捕获数据而又不完全依赖 Web 界面的高级用户和开发人员设计，使其成为任何 Openclaw Skills 集合的重要组成部分。

下载入口:https://github.com/openclaw/skills/tree/main/skills/leonardsellem/plaud-unofficial

安装与下载

1. ClawHub CLI

从源直接安装技能的最快方式。

2. 手动安装

将技能文件夹复制到以下位置之一

优先级：工作区 > 本地 > 内置

3. 提示词安装

将此提示词复制到 OpenClaw 即可自动安装。

Plaud API 应用场景

• 自动化将录音从 Plaud 硬件备份到本地或云存储。
• 以编程方式提取会议转录文本，以便集成到 PKM 工具或 CRM 中。
• 批量处理音频文件，用于研究、内容创作或数据分析。
• 访问 AI 生成的会议摘要，用于自动生成报告。
• 监控录音元数据，如时间戳、时长和文件夹标签。

1. 该技能使用从官方 Web 应用获取的载体令牌 (bearer token) 与 Plaud 后端进行身份验证。
2. 用户通过 plaud_client.py 工具与 API 交互，查询可用的录音和唯一文件 ID。
3. 客户端获取详细的元数据，包括分段的转录文本和 AI 处理的笔记。
4. 音频文件通过安全端点请求，并以 MP3 格式保存到指定的本地路径。
5. 输出可以格式化为 JSON，允许 Openclaw Skills 中的其他脚本或智能体进一步处理数据。

Plaud API 配置指南

要在您的 Openclaw Skills 设置中初始化此技能，请按照以下步骤操作：

1. 登录 https://web.plaud.ai，打开开发者工具 (F12)，在 Local Storage 中找到 tokenstr 和 plaud_user_api_domain 以获取您的凭据。
2. 进入技能目录并配置您的环境：

cd ~/.claude/skills/plaud-api
cat > .env << 'EOF'
PLAUD_TOKEN=bearer your_token_here
PLAUD_API_DOMAIN=https://api-euc1.plaud.ai
EOF

3. 安装所需的 Python 依赖项：

pip install -r requirements.txt

4. 通过列出您的录音来验证连接：

python3 plaud_client.py list

Plaud API 数据架构与分类体系

该技能将从 API 检索的数据组织成结构化格式，以便于使用：

name: plaud-api
description: Use when accessing Plaud voice recorder data (recordings, transcripts, AI summaries) - guides credential setup and provides patterns for plaud_client.py
aliases:
  - plaud
  - plaud-recordings

Plaud API Skill

Access Plaud voice recorder data including recordings, transcripts, and AI-generated summaries.

Overview

The Plaud API provides access to:

• Audio files: MP3 recordings from your Plaud device
• Transcripts: Full text transcriptions with speaker diarization
• AI summaries: Auto-generated notes and summaries

Core principle: Use plaud_client.py (included in this skill), not raw API calls. The client handles authentication, error handling, and response parsing.

When to Use This Skill

Use this skill when:

• User mentions "Plaud", "Plaud recording", or "transcript from Plaud"
• Need to access voice recorder data
• Working with recordings, transcripts, or AI notes from a Plaud device

Interactive Credential Tutorial

Before using the Plaud API, you need to extract credentials from the web app.

Step 1: Navigate to Plaud Web App

Open Chrome and go to: https://web.plaud.ai

Log in with your Plaud account if not already logged in.

Step 2: Open Chrome DevTools

Press F12 (or Cmd+Option+I on Mac) to open DevTools.

Step 3: Find localStorage Values

1. Click the Application tab in DevTools
2. In the left sidebar, expand Local Storage
3. Click on https://web.plaud.ai

Step 4: Copy Required Values

Find and copy these two values:

Step 5: Create .env File

Create or update the .env file in the skill directory (~/.claude/skills/plaud-api/):

# In the skill directory
cd ~/.claude/skills/plaud-api
cp .env.example .env
# Edit .env with your actual credentials

Or create it directly:

cat > ~/.claude/skills/plaud-api/.env << 'EOF'
PLAUD_TOKEN=bearer eyJ...your_full_token_here...
PLAUD_API_DOMAIN=https://api-euc1.plaud.ai
EOF

Important: Include the full token including the "bearer " prefix.

Step 6: Verify Setup

Test that credentials work:

cd ~/.claude/skills/plaud-api
python3 plaud_client.py list

If successful, you'll see a list of your recordings with file IDs, durations, and names.

First-time setup: Install dependencies if needed:

pip install -r ~/.claude/skills/plaud-api/requirements.txt

.env File Format

PLAUD_TOKEN=bearer eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9...
PLAUD_API_DOMAIN=https://api-euc1.plaud.ai

Notes:

• The token includes the "bearer " prefix
• API domain is region-specific (EU users: api-euc1, US users may differ)

Quick Reference

All commands should be run from the skill directory (~/.claude/skills/plaud-api):

Common Patterns

Fetch Recent Transcripts

cd ~/.claude/skills/plaud-api

# List files to find IDs
python3 plaud_client.py list

# Get transcript for a specific file
python3 plaud_client.py details  --json | jq '.data.trans_result'

File ID Discovery

File IDs are 32-character hex strings. Find them from:

1. URLs: https://web.plaud.ai/file/{file_id}
2. List output: First column in python3 plaud_client.py list
3. JSON output: python3 plaud_client.py list --json | jq '.[].id'

Get AI Summary

python3 plaud_client.py details  --json | jq '.data.ai_content'

Batch Operations

# Download all recordings to a folder
python3 plaud_client.py download-all -o ./all_recordings

# Get all file IDs
python3 plaud_client.py list --json | jq -r '.[].id'

Extract Transcript Text Only

# Get plain transcript text (all segments concatenated)
python3 plaud_client.py details  --json | jq -r '.data.trans_result.segments[].text' | tr '
' ' '

Error Handling

Token Refresh

Plaud tokens are long-lived (~10 months), but when they expire:

1. Log into https://web.plaud.ai
2. Open DevTools > Application > Local Storage
3. Copy the new tokenstr value
4. Update your .env file

API Reference

For detailed API documentation, see PLAUD_API.md included in this skill directory.

Key endpoints used by plaud_client.py:

• GET /file/simple/web - List all files
• GET /file/detail/{file_id} - Get file details with transcript
• GET /file/download/{file_id} - Download MP3 audio
• GET /filetag/ - Get file tags/folders

Included Files