Poetry Recitation
by @zhangyanbo2007
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...
clawhub install poetry-recitationπ About This Skill
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 "ζθ―΅", "θ―ζθ―΅", "θ―»δΈι¦θ―", (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
~/.openclaw/skills/tts-gen-pipeline/ with at least one cloned voicedashscope, websockets, moviepy, pillow, numpy/usr/share/fonts/opentype/noto/NotoSerifCJK-Regular.ttcQuick Start
python3 scripts/poetry_recitation.py --poem "εΊεζζε
\nηζ―ε°δΈι" --title "ιε€ζ"
or specify a voice:
python3 scripts/poetry_recitation.py --poem "..." --title "ιε€ζ" --voice η« ε½¦ε
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. η« ε½¦ε) or system voice (cherry/serena/ethan/chelsie). Default: first cloned voice |
| --output | No | Output video path (default: ~/workspace/audio/) |
Available Voices
Cloned voices: Check with python3 ~/.openclaw/skills/tts-gen-pipeline/scripts/generate.py list-local
System voices: cherry (ηηΎε₯³ε£°), serena (ζΈ©ζε₯³ε£°), ethan (ζ²η¨³η·ε£°), chelsie (η£ζ§η·ε£°)
Workflow
1. Accept poem text from user (and optional --voice preference)
2. Run poetry_recitation.py with the poem
3. Send the resulting video to user via MEDIA path β no extra confirmation needed
Voice Resolution
--voice matches a local cloned voice name β uses cloned voice model--voice matches a system voice name β uses system voice modelOutput
Generated video (1920x1080, 24fps, H.264 + AAC) saved to ~/workspace/audio/.
π‘ Examples
python3 scripts/poetry_recitation.py --poem "εΊεζζε
\nηζ―ε°δΈι" --title "ιε€ζ"
or specify a voice:
python3 scripts/poetry_recitation.py --poem "..." --title "ιε€ζ" --voice η« ε½¦ε
βοΈ Configuration
~/.openclaw/skills/tts-gen-pipeline/ with at least one cloned voicedashscope, websockets, moviepy, pillow, numpy/usr/share/fonts/opentype/noto/NotoSerifCJK-Regular.ttc