← 返回 Skills 市场

Chinese TTS

Name: Chinese TTS
Author: waao666

作者 Waao666 · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

497

总下载

当前安装

版本数

在 OpenClaw 中安装

/install chinese-tts

功能描述

Generate Chinese TTS audio and send as Feishu voice message. Use when user asks for voice/audio/语音/播报/朗读 in Chinese, or when sending audio messages via Feishu.

使用说明 (SKILL.md)

Chinese TTS Voice Generation

Generate natural Chinese speech using Microsoft Edge TTS and send as Feishu voice messages.

Quick Reference

# 1. Generate MP3
LANG=en_US.UTF-8 LC_ALL=en_US.UTF-8 /home/clawpi/.local/bin/edge-tts \
  --voice zh-CN-YunxiNeural \
  --text "你的文本内容" \
  --write-media /tmp/output.mp3

# 2. Convert to Opus
ffmpeg -i /tmp/output.mp3 -c:a libopus -b:a 64k -ar 48000 \
  /home/node/.openclaw/workspace/output.opus -y

# 3. Send via Feishu
message(asVoice=true, contentType="audio/ogg",
        filePath="/home/node/.openclaw/workspace/output.opus",
        filename="output.opus")

Critical Rules

Always set UTF-8 env vars — System locale is ISO-8859-1, Chinese text will be corrupted without LANG=en_US.UTF-8 LC_ALL=en_US.UTF-8
Must use opus format — Feishu only treats .opus as voice messages; MP3/WAV become file attachments
Must send from workspace — /tmp is not in Feishu's mediaLocalRoots whitelist; files there fail silently and fall back to plain text
Use ASCII filenames — Chinese filenames may cause encoding issues in multipart uploads

Voice Options

Voice	Gender	Style
`zh-CN-YunxiNeural`	Male	Natural, warm (recommended)
`zh-CN-XiaoxiaoNeural`	Female	Natural, friendly
`zh-CN-YunjianNeural`	Male	Authoritative

For Long Text

Write text to a file and use -f flag:

echo "长文本内容..." > /tmp/text.txt
LANG=en_US.UTF-8 LC_ALL=en_US.UTF-8 /home/clawpi/.local/bin/edge-tts \
  --voice zh-CN-YunxiNeural -f /tmp/text.txt --write-media /tmp/output.mp3

Troubleshooting

Gibberish audio → Missing UTF-8 env vars
File sent as attachment, not voice → Not opus format, or not from workspace path
Upload fails silently → File not in mediaLocalRoots (use workspace dir)
"哈米" instead of "虾米" → Google TTS (gtts) issue; use edge-tts instead

安全使用建议

This skill appears to do what it says (generate Chinese TTS and prepare an opus file for Feishu), but review before installing: 1) Confirm you trust the edge-tts binary at /home/clawpi/.local/bin/edge-tts (it may contact Microsoft servers to synthesize speech). 2) Ensure ffmpeg is available and that the workspace path (/home/node/.openclaw/workspace or equivalent) exists and is writable by the agent — the script assumes hard-coded absolute paths that may not match your environment. 3) The package metadata does not declare required binaries; treat this as a configuration/packaging bug and either update the skill metadata or adapt paths. 4) Verify your Feishu integration and mediaLocalRoots policy — the SKILL.md relies on the platform to upload the generated .opus file. 5) If you need stronger assurance, run the script in an isolated environment, or replace hard-coded paths with configurable ones and audit the edge-tts binary/source before use.

功能分析

Type: OpenClaw Skill Name: chinese-tts Version: 1.0.0 The skill bundle provides legitimate functionality for generating Chinese text-to-speech audio using Microsoft Edge TTS and converting it for Feishu voice messages. The instructions in SKILL.md and the logic in scripts/generate_voice.sh are consistent with the stated purpose, using standard tools like ffmpeg and edge-tts without any signs of data exfiltration, persistence, or malicious prompt injection.

能力评估

⚠ Purpose & Capability

The skill claims no required binaries or env vars, but both SKILL.md and scripts call /home/clawpi/.local/bin/edge-tts and ffmpeg and reference a workspace path (/home/node/.openclaw/workspace). Requiring edge-tts and ffmpeg is appropriate for a TTS-to-Feishu skill, but the skill metadata should declare those binaries and not rely on hard-coded user-specific absolute paths.

ℹ Instruction Scope

Instructions and script are narrowly focused on generating MP3 via edge-tts, converting to opus with ffmpeg, and sending via Feishu. They do not attempt to read unrelated system secrets. However examples and the script use /tmp and hard-coded workspaces and show a pseudo call message(...); the actual Feishu send relies on platform integration being present and correctly configured.

ℹ Install Mechanism

No install spec (instruction-only) — low installation risk. But the skill assumes presence of external binaries (edge-tts, ffmpeg) which are not declared. The edge-tts binary path is non-standard and user-specific, which is an operational concern (could run an unexpected binary if path differs).

✓ Credentials

The skill requests no credentials and the script only exports UTF-8 locale env vars. No secrets are requested. Be aware that edge-tts is a Microsoft client and may send text to remote services (expected for that tool).

✓ Persistence & Privilege

always is false and the skill does not request or change persistent agent/system configuration. It does not ask to modify other skills or system-wide settings.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install chinese-tts
安装完成后，直接呼叫该 Skill 的名称或使用 /chinese-tts 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Edge TTS + Feishu opus voice messages

元数据

Slug chinese-tts

版本 1.0.0

许可证 —

累计安装 1

当前安装数 1

历史版本数 1

常见问题

Chinese TTS 是什么？

Generate Chinese TTS audio and send as Feishu voice message. Use when user asks for voice/audio/语音/播报/朗读 in Chinese, or when sending audio messages via Feishu. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 497 次。

如何安装 Chinese TTS？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install chinese-tts」即可一键安装，无需额外配置。

Chinese TTS 是免费的吗？

是的，Chinese TTS 完全免费（开源免费），可自由下载、安装和使用。

Chinese TTS 支持哪些平台？

Chinese TTS 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 Chinese TTS？

由 Waao666（@waao666）开发并维护，当前版本 v1.0.0。