gitbyeos/open-part-skills · Archived

voice-to-me

将回复生成 MP3 语音并通过 QQ 发送。用户要求语音回复、音频回复、朗读、“语音回复”、“发语音”、“读给我听”,或希望答案以语音形式交付时使用

First seen Aug 7, 2026

Installation

$ npx skills add gitbyeos/open-part-skills --skill voice-to-me

Stronger alternatives

This repository is archived — consider an actively maintained alternative.

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from gitbyeos/open-part-skills · top by installs.

npx skills add gitbyeos/open-part-skills

Browse all from gitbyeos/open-part-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 40
License LICENSE
Default branch main
Open issues 0
Status Archived

Skill metadata

Parsed from SKILL.md frontmatter.

Version1.0.0

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 2,452 B
  • docs SUMMARY.md 223 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 1 installs

SKILL.md

语音回复

将回答整理为简洁自然的口语稿,在当前会话工作区生成 MP3,并通过 QQ 返回

依赖

python3 -m pip install "edge-tts>=7.0,<8"

系统还须安装 ffmpeg,用于默认降噪和追加尾部静音

生成音频

  1. 保持朗读文本自然,移除 Markdown 语法、不应朗读的 URL、文件标签和模型或会话元数据。
  2. 输出必须位于当前工作目录,QQ 网关才能接收。默认路径为 .qq-voice/reply-<timestamp>.mp3
  3. 从可用 Skills 列表中获取本 Skill 的目录路径,然后运行:
python3 "<skill-dir>/scripts/voice_to_me.py" \
  --text "要朗读的内容" \
  --output "$PWD/.qq-voice/reply-$(date +%Y%m%d-%H%M%S).mp3"

默认人设配置:xiaoyi(zh-CN-XiaoyiNeural)、+7Hz 音高和 --rate 1.13(+13% 语速)。仅当用户明确偏好更成熟的声音时,才使用 --voice xiaoxiao

参数 默认值 说明
--voice xiaoyi 音色;用户明确偏好成熟音色时使用 xiaoxiao
--rate 1.13 语速,范围 0.5–2.0
--tail-silence 0.5 语音结尾静音秒数,范围 0–5
--denoise 开启 轻度高通、去齿音、低通,抑制低频隆隆声与高频嘶声
--no-denoise 关闭降噪 仅在用户要求保留原始音色时使用

对于较长或含 Shell 特殊字符的文本,将朗读内容保存到会话工作区,再使用 --text-file <path> 代替 --text

默认开启轻度降噪,并通过 MP3 流复制追加尾部静音,避免为停顿而二次编码。降噪会额外消耗少量 CPU 并重新编码音频;它不一定能消除合成语音本身的高频纹理,因此需要保留原始音色时使用 --no-denoise

通过 QQ 返回

成功生成后,在最终回复中单独另起一行添加以下标签:

<qqvoice>/absolute/path/to/reply.mp3</qqvoice>
  • 使用脚本打印的绝对路径。不要将该标签置于 Markdown 代码块中
  • 语音回复时不需要回复其他文字