← Back to Skills Marketplace
kaqzsd

feishu voice reply

by chenji · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
315
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install feishu-voice-reply-huoshan
Description
通过火山引擎 TTS 合成多音色语音，转换为 Opus 格式后，使用飞书 API 自动上传并发送语音消息。
README (SKILL.md)

飞书语音回复技能 (Feishu Voice Reply)

描述

使用火山引擎 TTS 生成特色音色语音，通过飞书 API 发送语音消息的完整流程技能。支持 MP3 转 Opus 格式、自动上传和发送。

触发词

  • 语音回复
  • 发送语音
  • TTS 语音
  • 飞书语音
  • @voice

前置配置

1. 环境变量设置

在 ~/.openclaw/.env 或系统环境变量中配置：

# 火山引擎 TTS 配置
export VOLC_API_KEY="你的火山引擎 API Key"
export VOLC_RESOURCE_ID="volc.service_type.10029"

# 飞书应用配置
export FEISHU_APP_ID="你的飞书 App ID"
export FEISHU_APP_SECRET="你的飞书 App Secret"

# 可选：默认接收者 Open ID
export FEISHU_DEFAULT_USER_ID="ou_xxxxxx"

2. 安装依赖

# 安装 ffmpeg（用于音频格式转换）
# Ubuntu/Debian
sudo apt install ffmpeg

# macOS
brew install ffmpeg

# CentOS/RHEL
sudo yum install ffmpeg

3. 火山引擎开通

  1. 访问 https://www.volcengine.com/
  2. 注册/登录账号
  3. 开通语音合成服务
  4. 获取 API Key
  5. 创建资源包并获取 Resource ID

4. 飞书应用配置

  1. 访问 https://open.feishu.cn/app
  2. 创建企业自建应用
  3. 获取 App ID 和 App Secret
  4. 添加权限：
    • im:resource - 上传资源文件
    • im:message - 发送消息
    • contact:user.base:readonly - 读取用户信息
  5. 发布应用

使用方法

命令行方式

# 基本用法（使用默认音色）
./scripts/feishu-voice-reply.sh "你好呀，这是测试语音"

# 指定音色
./scripts/feishu-voice-reply.sh "你好" "ICL_zh_female_tiaopigongzhu_tob"

# 指定音色和接收者
./scripts/feishu-voice-reply.sh "你好" "ICL_zh_female_tiaopigongzhu_tob" "ou_xxxxxx"

OpenClaw 方式

语音回复 "你好呀，我是语音助手"

可用音色

当前资源包可用音色

音色 ID 名称 风格 性别
ICL_zh_female_tiaopigongzhu_tob 调皮公主 活泼可爱 女
zh_male_beijingxiaoye_emo_v2_mars_bigtts 北京小爷 emo 北京腔 男

更多音色

完整音色列表: 火山引擎音色列表

女声音色（部分）

  • 弯弯笑 zh_female_wanwanxiao_mars_bigtts - 甜美
  • 晶晶 zh_female_jingjing_mars_bigtts - 清新
  • 轻婉 zh_female_qingwan_mars_bigtts - 温柔
  • 新晴 zh_female_xinqing_mars_bigtts - 阳光
  • 甜美 zh_female_tianmei_mars_bigtts - 甜美

男声音色（部分）

  • 北京小爷 zh_male_beijingxiaoye_mars_bigtts - 北京腔
  • 爽快 zh_male_shuangkuai_mars_bigtts - 爽朗
  • 青春 zh_male_qingchun_mars_bigtts - 青春

注意: 以上音色需要开通对应的资源包才能使用。

执行流程

用户输入文本
    ↓
1. 调用火山引擎 TTS API → 生成 MP3 音频
    ↓
2. 使用 ffmpeg 转换 → Opus 格式 (32kbps)
    ↓
3. 调用飞书 API → 获取 Access Token
    ↓
4. 上传 Opus 文件 → 获取 file_key
    ↓
5. 发送语音消息 → 飞书用户

文件结构

feishu-voice-reply-clean/
├── SKILL.md                      # 技能说明（本文件）
├── README.md                     # 使用文档
├── package.json                  # 包配置
├── scripts/
│   └── feishu-voice-reply.sh     # 自动化脚本
└── config/
    └── feishu-voice-config.json  # 配置模板

错误处理

错误 原因 解决方案
resource ID is mismatched 音色不在资源包中 更换可用音色
99991661 缺少 access token 检查飞书应用配置
99992402 缺少 receive_id_type 已自动处理
ffmpeg not found 未安装 ffmpeg 安装 ffmpeg
VOLC_API_KEY not set 未配置环境变量 设置环境变量

配置文件说明

环境变量

变量名 说明 是否必需
VOLC_API_KEY 火山引擎 API Key ✅ 必需
VOLC_RESOURCE_ID 火山引擎资源 ID ✅ 必需
FEISHU_APP_ID 飞书应用 App ID ✅ 必需
FEISHU_APP_SECRET 飞书应用 App Secret ✅ 必需
FEISHU_DEFAULT_USER_ID 默认接收者 Open ID ❌ 可选

配置模板

复制 config/feishu-voice-config.json 为 config/feishu-voice-config.local.json 并进行个性化配置。

安全提示

  • ⚠️ 不要将 API Key 和 App Secret 提交到代码仓库
  • ⚠️ 使用环境变量存储敏感信息
  • ✅ 配置文件已加入 .gitignore
  • ✅ 生产环境使用独立的密钥管理

相关文档

更新日志

v1.0.0 (2026-03-13)

  • ✅ 初始版本发布
  • ✅ 支持火山引擎 TTS 多音色
  • ✅ 支持飞书语音消息发送
  • ✅ 自动 MP3 转 Opus 格式
  • ✅ 完整错误处理
  • ✅ 详细文档

最后更新：2026-03-13 | 作者：沉寂 (chenji) | License: MIT

Usage Guidance
This skill does what it says (Volcengine TTS → convert → Feishu). Before installing or running it: 1) Treat FEISHU_APP_SECRET and VOLC_API_KEY as sensitive — use a secrets manager or ensure ~/.openclaw/.env is protected. 2) Do not rely on the registry metadata: the skill DOES require VOLC_API_KEY, VOLC_RESOURCE_ID, FEISHU_APP_ID and FEISHU_APP_SECRET. 3) Ensure the host has ffmpeg and jq installed (SKILL.md only mentions ffmpeg). 4) Review and test the script in a safe environment — the script embeds user text directly into JSON bodies without escaping and has a probable tmp-filename bug; these should be fixed to avoid malformed requests or accidental file collisions. 5) Create a Feishu app with minimal required permissions and rotate keys if you test with production credentials. If you want to proceed, ask the author to (a) correct registry metadata to list required env vars, (b) document jq as a required tool, and (c) fix the tmp filename and JSON-escaping in scripts.
Capability Analysis
Type: OpenClaw Skill Name: feishu-voice-reply-huoshan Version: 1.0.0 The skill bundle provides a legitimate utility for generating voice messages via Volcengine TTS and sending them through the Feishu (Lark) API. The core logic in `scripts/feishu-voice-reply.sh` uses standard API calls to official endpoints (openspeech.bytedance.com and open.feishu.cn), handles temporary files safely in /tmp, and correctly instructs users to manage sensitive credentials via environment variables. No evidence of data exfiltration, malicious execution, or prompt injection was found.
Capability Assessment
⚠ Purpose & Capability
The skill's stated purpose (generate TTS with 火山引擎 and send via 飞书) matches the code: the script calls Volcengine and Feishu endpoints and converts with ffmpeg. However the registry metadata claims no required environment variables while SKILL.md and the script require VOLC_API_KEY, VOLC_RESOURCE_ID, FEISHU_APP_ID, and FEISHU_APP_SECRET—an important metadata mismatch that can mislead automated installers or reviewers. package.json also lists an npm dependency "ffmpeg": "*" which is not a real npm runtime dependency for a shell script and looks incorrect.
⚠ Instruction Scope
The SKILL.md instructions and the script stay within the declared purpose: they only call Volcengine and Feishu endpoints, convert audio with ffmpeg, and upload to Feishu. No unrelated system files or external endpoints are referenced. Concerns: (1) the bash script uses user-supplied TEXT directly inside JSON body without escaping — this can break requests or lead to malformed payloads if text contains quotes/newlines; (2) the script uses jq and ffmpeg but only ffmpeg is mentioned in SKILL.md (jq is not documented as required); (3) a likely bug in tmp filename (TMP_MP3="/tmp/voice-tts-$.mp3") may create unexpected filenames or collisions.
ℹ Install Mechanism
This is an instruction-only skill (no install spec) and therefore does not fetch or execute remote archives—low installation risk. The included files are a shell script and config templates. Minor oddity: package.json lists "ffmpeg" under dependencies which is inappropriate for a shell-based skill and could confuse some package managers.
⚠ Credentials
The environment variables required by the skill (VOLC_API_KEY, VOLC_RESOURCE_ID, FEISHU_APP_ID, FEISHU_APP_SECRET, optional FEISHU_DEFAULT_USER_ID) are appropriate and necessary for the stated purpose. The concern is that the registry metadata claims 'no required env vars' while the SKILL.md and script require sensitive credentials—this mismatch is misleading and dangerous if users assume no secrets are needed. The skill requests only the service-specific credentials it needs (no unrelated secrets).
✓ Persistence & Privilege
The skill does not request always:true and does not attempt to modify other skills or system-wide configuration. It runs as an on-demand script and requires explicit environment setup; privilege/persistence requests are minimal and appropriate.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install feishu-voice-reply-huoshan
  3. After installation, invoke the skill by name or use /feishu-voice-reply-huoshan
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
飞书语音回复技能 v1.0.0 - 初始版本发布，完成火山引擎 TTS 语音生成到飞书消息发送全流程 - 支持多种音色选择及格式转换（自动从 MP3 转 Opus） - 支持通过命令行或关键词触发使用 - 提供详细的依赖安装、配置与错误处理说明 - 包含丰富的文档和环境变量示例
Metadata
Slug feishu-voice-reply-huoshan
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is feishu voice reply?

通过火山引擎 TTS 合成多音色语音，转换为 Opus 格式后，使用飞书 API 自动上传并发送语音消息。 It is an AI Agent Skill for Claude Code / OpenClaw, with 315 downloads so far.

How do I install feishu voice reply?

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

Is feishu voice reply free?

Yes, feishu voice reply is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does feishu voice reply support?

feishu voice reply is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created feishu voice reply?

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

More Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 Comments