← Back to Skills Marketplace
anightmare2

Feishu Edge Tts

by Anightmare2 · GitHub ↗ · v1.0.0
cross-platform ⚠ suspicious
492
Downloads
0
Stars
4
Active Installs
1
Versions
Install in OpenClaw
/install feishu-edge-tts
Description
使用微软 Edge TTS(免费)生成语音,发送到飞书。无需 API key,音质优秀,支持多语言多音色。
README (SKILL.md)

Feishu Edge TTS - 飞书语音条(微软免费 TTS)

使用微软 Edge TTS 生成语音,发送到飞书!完全免费

🎯 功能特点

  • 完全免费:使用微软 Edge TTS,无需 API key
  • 音质优秀:微软 Azure 同款语音引擎
  • 多音色支持:支持中文/英文/日文等多种语言
  • 语音条格式:发送真正的飞书语音条(点击即播)
  • 语速调节:支持 0.5x - 2.0x 语速
  • 音调调节:支持音调高低调整

🎤 可用音色

中文音色

  • zh-CN-XiaoxiaoNeural - 女声,温暖亲切(推荐)
  • zh-CN-YunxiNeural - 男声,沉稳专业
  • zh-CN-YunjianNeural - 男声,激情澎湃
  • zh-CN-XiaoyiNeural - 女声,活泼可爱
  • zh-CN-liaoning-XiaobeiNeural - 东北话女声
  • zh-CN-shaanxi-XiaoniNeural - 陕西话女声

英文音色

  • en-US-JennyNeural - 女声,美式英语(推荐)
  • en-US-GuyNeural - 男声,美式英语
  • en-GB-SoniaNeural - 女声,英式英语

更多音色

支持全球 100+ 语言,400+ 音色!

🔧 前置要求

1. Python 环境

# 安装 edge-tts
pip install edge-tts

2. Feishu 应用配置

同 Feishu Voice Skill

3. 系统依赖

# 安装 ffmpeg
yum install -y ffmpeg  # CentOS/OpenCloudOS
apt-get install -y ffmpeg  # Ubuntu/Debian

🚀 快速开始

步骤 1:安装依赖

pip install edge-tts

步骤 2:配置环境变量

export FEISHU_APP_ID="cli_xxx"
export FEISHU_APP_SECRET="xxx"
export FEISHU_CHAT_ID="oc_xxx"

步骤 3:发送语音

# 使用默认音色(女声)
bash scripts/send_voice.sh -t "主人晚上好~"

# 指定音色
bash scripts/send_voice.sh -t "Hello!" -v en-US-JennyNeural

# 调整语速
bash scripts/send_voice.sh -t "你好" --rate 1.2

# 调整音调
bash scripts/send_voice.sh -t "你好" --pitch 10

💡 使用示例

1. 温暖女声问候

bash scripts/send_voice.sh -t "主人早上好~ 新的一天开始啦,今天也要加油哦~" -v zh-CN-XiaoxiaoNeural

2. 专业男声播报

bash scripts/send_voice.sh -t "现在是北京时间上午 8 点,为您播报今日新闻。" -v zh-CN-YunxiNeural

3. 英文语音

bash scripts/send_voice.sh -t "Good morning! Have a nice day!" -v en-US-JennyNeural

4. 方言趣味

bash scripts/send_voice.sh -t "哎呀妈呀,这旮瘩真冷啊!" -v zh-CN-liaoning-XiaobeiNeural

📖 命令参数

bash scripts/send_voice.sh [选项]

选项:
  -t, --text \x3Ctext>       要转换的文字(必需)
  -v, --voice \x3Cvoice>     音色名称(默认:zh-CN-XiaoxiaoNeural)
  -r, --rate \x3C1.0>        语速(-50% 到 +50%,默认 0%)
  -p, --pitch \x3C0>         音调(-50Hz 到 +50Hz,默认 0)
  -o, --output \x3Cfile>     输出音频文件路径
  --list-voices           列出所有可用音色
  --no-send               只生成音频,不发送
  -h, --help              显示帮助

🎵 音色列表

# 查看所有可用音色
bash scripts/send_voice.sh --list-voices

# 查看中文音色
bash scripts/send_voice.sh --list-voices | grep zh-CN

⚙️ 高级配置

1. 自定义默认音色

编辑 config.sh

DEFAULT_VOICE="zh-CN-YunxiNeural"  # 男声
DEFAULT_RATE="0"                    # 正常语速
DEFAULT_PITCH="0"                   # 正常音调

2. 批量生成

# 从文件读取文字,批量生成
cat messages.txt | while read line; do
    bash scripts/send_voice.sh -t "$line"
    sleep 2
done

📦 文件结构

feishu-edge-tts/
├── SKILL.md
├── README.md
├── reference.md
├── scripts/
│   ├── send_voice.sh        # 主脚本
│   ├── list_voices.sh       # 音色列表
│   └── config.sh            # 配置文件
├── examples/
│   ├── greetings.txt        # 问候语示例
│   └── crontab.txt          # 定时任务示例
└── config.sh                # 用户配置

💰 商业授权

  • 个人使用:免费
  • 商业使用:请联系作者获取授权

Made with ❤️ by 司幼 (SiYou)

Usage Guidance
This skill appears to do what it claims (generate Edge TTS audio and send it to Feishu). Before installing or running: - Note that you must provide FEISHU_APP_ID, FEISHU_APP_SECRET, and FEISHU_CHAT_ID as environment variables; the top-level registry metadata omitted these — don't trust that omission. - Create or use a Feishu app/account with the minimum permissions necessary (least privilege) for uploading and sending messages; avoid using highly privileged tenant credentials. - Inspect scripts yourself (or run them in an isolated environment) — the send_voice.sh script posts only to open.feishu.cn and uses local temp files, edge-tts, ffmpeg, curl, and python3 for JSON parsing. There are no hidden remote endpoints in the code. - Test with the --no-send flag first to confirm audio generation locally before providing real Feishu credentials. - Install edge-tts and ffmpeg from official package sources (pip and your OS package manager) to avoid malicious third-party binaries. If you want higher assurance, ask the author for canonical source (repo/homepage) and a signed release; the manifest claims a GitHub URL but 'Source' and 'Homepage' are unknown — lack of an authoritative upstream repo reduces confidence.
Capability Analysis
Type: OpenClaw Skill Name: feishu-edge-tts Version: 1.0.0 The skill provides legitimate functionality to convert text to speech using Microsoft Edge TTS and send it to Feishu. However, the main script `scripts/send_voice.sh` is vulnerable to shell injection because it passes unsanitized user-provided arguments (such as the text content and voice selection) directly into shell commands for `edge-tts` and `ffmpeg`. While no evidence of intentional malice or unauthorized data exfiltration was found, the lack of input validation represents a significant security flaw.
Capability Assessment
Purpose & Capability
The name/description (Edge TTS → Feishu) match what the scripts do: use edge-tts, ffmpeg, and curl to generate audio and upload/send via Feishu APIs. Required tools (edge-tts, ffmpeg, curl) are appropriate for this purpose.
Instruction Scope
SKILL.md and scripts scope is limited to generating audio (edge-tts), converting to opus (ffmpeg), uploading to Feishu via open.feishu.cn, and sending a message. The runtime instructions do not read unrelated system files or attempt to exfiltrate data to unexpected endpoints.
Install Mechanism
No install spec; this is instruction + script based. Dependencies are installed via standard channels (pip for edge-tts, OS package managers for ffmpeg) which is low risk compared to downloading arbitrary binaries.
Credentials
The scripts require FEISHU_APP_ID, FEISHU_APP_SECRET, and FEISHU_CHAT_ID to upload/send audio—this is proportionate to sending messages via Feishu. However, the registry summary at the top incorrectly listed 'Required env vars: none' while clawhub.yaml and SKILL.md do declare/expect these env vars. That metadata mismatch is a red flag (could be oversight, but it affects informed consent before installation).
Persistence & Privilege
Skill does not request persistent elevated privileges, does not set always:true, and does not modify other skills or global configs. It runs as a normal script and cleans up temporary files.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install feishu-edge-tts
  3. After installation, invoke the skill by name or use /feishu-edge-tts
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release - 微软免费 TTS,400+ 音色
Metadata
Slug feishu-edge-tts
Version 1.0.0
License
All-time Installs 4
Active Installs 4
Total Versions 1
Frequently Asked Questions

What is Feishu Edge Tts?

使用微软 Edge TTS(免费)生成语音,发送到飞书。无需 API key,音质优秀,支持多语言多音色。 It is an AI Agent Skill for Claude Code / OpenClaw, with 492 downloads so far.

How do I install Feishu Edge Tts?

Run "/install feishu-edge-tts" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Feishu Edge Tts free?

Yes, Feishu Edge Tts is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Feishu Edge Tts support?

Feishu Edge Tts is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Feishu Edge Tts?

It is built and maintained by Anightmare2 (@anightmare2); the current version is v1.0.0.

💬 Comments