Poetry Recitation

该 Skill 接收诗文与标题，调用本地 TTS 管线或系统音色合成朗诵语音，再用视频合成脚本叠加星空背景与定时中文字幕，输出 1920x1080、24fps 的 H.264+AAC 视频文件。

zhangyanbo2007

热度 46.52

最近更新 2026-05-11 17:44:32

分类：创作依赖：代码执行 / 读写文件 / 第三方 API应用场景：视频编辑 / 故事创作

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add poetry-recitation

Metadata

name: poetry-recitation
description: Generate poetry recitation videos using a cloned voice or system voice with starry background and Chinese subtitles. Use when: (1) User asks to recite a poem, (2) User says "朗诵", "诗朗诵", "读一首诗", (3) User wants a video with voice + subtitles for any poem or literary text. NOT for: AI-generated video backgrounds, music generation, or non-poetry text-to-speech.

Poetry Recitation

Generate a video: voice recitation + starry background + timed Chinese subtitles.

Prerequisites

TTS pipeline at ~/.openclaw/skills/tts-gen-pipeline/ with at least one cloned voice
Dependencies: dashscope, websockets, moviepy, pillow, numpy
Font: NotoSerifCJK at /usr/share/fonts/opentype/noto/NotoSerifCJK-Regular.ttc

Quick Start

python3 scripts/poetry_recitation.py --poem "床前明月光\n疑是地上霜" --title "静夜思"
# or specify a voice:
python3 scripts/poetry_recitation.py --poem "..." --title "静夜思" --voice 章彦博

Arguments

Arg	Required	Description
`--poem`	Yes	Poem text, use `\n` for line breaks
`--title`	No	Title displayed at top of video
`--voice`	No	Voice name: cloned voice (e.g. 章彦博) or system voice (cherry/serena/ethan/chelsie). Default: first cloned voice
`--output`	No	Output video path (default: `~/workspace/audio/<title>_朗诵.mp4`)

Available Voices

Cloned voices: Check with python3 ~/.openclaw/skills/tts-gen-pipeline/scripts/generate.py list-local

System voices: cherry (甜美女声), serena (温柔女声), ethan (沉稳男声), chelsie (磁性男声)

Workflow

Accept poem text from user (and optional --voice preference)
Run poetry_recitation.py with the poem
Send the resulting video to user via MEDIA path — no extra confirmation needed

Voice Resolution

If --voice matches a local cloned voice name → uses cloned voice model
If --voice matches a system voice name → uses system voice model
If not specified → uses first available cloned voice

Output

Generated video (1920x1080, 24fps, H.264 + AAC) saved to ~/workspace/audio/.