Feishu Edge TTS Voice

飞书语音消息发送技能。使用 Edge TTS（微软，免费无限次）生成语音并以飞书语音气泡形式发送。当用户要求用语音回复、发语音消息、TTS 朗读内容时触发。默认音色：云希（zh-CN-YunxiNeural，活泼阳光男声）。

Security Scan

The skill appears to do what it claims (generate Edge TTS and send an audio bubble to Feishu), but it silently reads your ~/.openclaw/openclaw.json for Feishu appId/appSecret and the registry metadata does not declare this required credential/config path — a mismatch that deserves attention before installing.

Purpose & Capability

The skill's functionality (Edge TTS -> convert -> upload to Feishu) matches the code and instructions. However, the package metadata declares no required credentials or config paths while the runtime script expects a ~/.openclaw/openclaw.json containing feishu appId/appSecret. That omission is an inconsistency: the skill does need Feishu credentials (in a config file) even though the registry metadata lists none.

Instruction Scope

SKILL.md and the script keep to a narrow scope: generate audio with edge-tts, convert with ffmpeg, obtain a Feishu tenant token, upload the opus file, and send an audio message. Network calls go only to open.feishu.cn and no other external endpoints. One scope note: the script loads the entire openclaw.json and then accesses cfg['channels']['feishu'] — it only uses feishu fields, but because it reads the whole config file it could access other secrets if modified.

Install Mechanism

There is no automated install spec (instruction-only plus a script). The README tells users to pip install edge-tts and to ensure ffmpeg is present. This is low-risk compared with arbitrary download-and-extract installs. Users should still install edge-tts/ffmpeg from trusted sources.

Credentials

The skill requires Feishu app credentials (appId/appSecret) but does not declare them in requires.env or required config paths in the registry metadata; instead it expects them inside ~/.openclaw/openclaw.json. That mismatch is a proportionality/visibility problem. Also, because the script opens the entire JSON file, if you keep other sensitive credentials there they could be read into memory — the script currently only uses the Feishu fields, but the practice means sensitive data is being accessed without being declared.

Persistence & Privilege

The skill is not always-included and is user-invocable. It does not modify other skills or system configuration. No elevated persistence privileges are requested.

What to consider before installing

Before installing or running this skill: (1) Inspect ~/.openclaw/openclaw.json and confirm it contains only the Feishu appId/appSecret you intend to use — don't point the script at a file containing broad secrets. (2) Prefer creating a Feishu app with minimal permissions for this purpose. (3) Because the registry metadata does not declare the required config/credentials, treat that omission as a red flag: either ask the publisher to update the metadata or avoid installing until it's fixed. (4) Review the included scripts/send_voice.py yourself (it is small and readable); if you run it, do so in an environment where executing curl/ffmpeg/edge-tts is acceptable (or sandboxed). (5) If you want stronger guarantees, request the skill be updated to accept credentials via a clearly-declared config path or dedicated environment variables (and update registry metadata accordingly). Additional info that would raise confidence to 'high': metadata that explicitly declares the required config path and primary credential, or an updated script that only reads a minimal, well-documented credentials file.

飞书语音消息发送

快速使用

python3 ~/.openclaw/workspace/skills/feishu-voice/scripts/send_voice.py \
  "要说的内容" \
  <open_id>

工作流程

1. edge-tts 生成 mp3
2. ffmpeg 转换为 opus（飞书语音格式）
3. 飞书 API 上传文件获取 file_key（file_type=opus）
4. 发送 msg_type=audio 消息

关键：必须用 msg_type: audio + file_key，不能用普通文件上传，否则显示为文件而非语音气泡。

音色选择

# 查看所有中文音色
edge-tts --list-voices | grep zh-CN

# 常用中文男声
zh-CN-YunxiNeural    # 云希 - 活泼阳光（默认，小龙虾专用）
zh-CN-YunjianNeural  # 云间 - 激情澎湃
zh-CN-YunxiaNeural   # 云夏 - 可爱萌
zh-CN-YunyangNeural  # 云扬 - 专业严肃

# 常用中文女声
zh-CN-XiaoxiaoNeural # 小小 - 温柔
zh-CN-XiaoyiNeural   # 小艺 - 活泼

# 指定音色发送
python3 ~/.openclaw/workspace/skills/feishu-voice/scripts/send_voice.py \
  "内容" <open_id> --voice zh-CN-YunyangNeural

依赖安装

pip install edge-tts  # 一次性安装，永久免费
# ffmpeg 通常已预装，如没有：yum install ffmpeg / apt install ffmpeg

飞书配置

需要 openclaw.json 中的 feishu appId / appSecret，脚本自动读取。