Agent Skills: audio-tts

When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a).

UncategorizedID: cklxx/elephant.ai/audio-tts

Install this agent skill to your local

pnpm dlx add-skill https://github.com/cklxx/elephant.ai/tree/HEAD/skills/audio-tts

Skill Files

Browse the full folder contents for audio-tts.

Download Skill

Loading file tree…

skills/audio-tts/SKILL.md

Skill Metadata

Name
audio-tts
Description
When the user wants text-to-speech audio → generate voice files locally (macOS say + afconvert, outputs m4a).

audio-tts

使用 macOS 自带 say 生成语音,并转成 m4a。

Requirements

  • macOS(内置 say
  • afconvert(macOS 自带)

Usage

python3 skills/audio-tts/run.py speak --text '你好,这是语音测试'

Parameters

speak

| 参数 | 类型 | 必填 | 说明 | |------|------|------|------| | text | string | 是 | 朗读文本 | | voice | string | 否 | voice 名称(如 Ting-Ting / Samantha),默认空(系统默认) | | rate | int | 否 | 语速 WPM(say 的 -r 参数) | | output | string | 否 | 输出路径(默认 /tmp/tts_<ts>.m4a) |