← Back to list
video-voiceover Checked
A skill from the GitHub repository zenstory-ai/video-recap-skills.
8.6Overall rating
Installation
🤖 Install via AI
Copy the prompt below and send it to your AI assistant (e.g. Claude Code) — it will follow the instructions and install automatically.
Install the "video-voiceover" skill by following the instructions at https://skill123.me/install/video-voiceover.
⌨️ Command line install
Run in your terminal — downloads and installs to ~/.claude/skills/.
curl -fsSL https://skill123.me/install/video-voiceover.sh | bash
📦 Download ZIP
Download the zip and extract it into your skills directory (e.g. ~/.claude/skills/), then restart your session.
⬇ Download v1.0.0 · 31 KBAbout this skill
Overview
A skill from the GitHub repository zenstory-ai/video-recap-skills.
Source
- Repo: https://github.com/zenstory-ai/video-recap-skills
- Path: skills/video-voiceover
Score breakdown
Trigger
7.0
Clear stage description naming both TTS providers and models with bilingual trigger words; no explicit When-Not in the description.
Structure
8.7
81-line SKILL.md over 5 focused scripts; no references tier, minimal but appropriate.
Workflow
8.8
Good execution design: content+settings fingerprinted caching (only affected WAVs regenerate), partial-failure policy keeping missing speech visible, provider fallback rules, and a deterministic dub lint gate before cloning.
Content
9.0
Precise contracts and env documentation; consistent with sibling skills.
Engineering
8.0
Valid frontmatter; entry script lacks a shebang (documented python3 invocation); env surface fully documented.
Security
10.0
Capability manifest matches declared scope: cloud TTS providers named in the description, reference-audio upload for cloning explicitly disclosed and gated on user authorization, API keys sanitized out of error text, no other network, no persistence.
TTS stage of the zenstory-ai video-recap pipeline: synthesizes per-segment narration audio via MiMo TTS or Fish Audio with time-window speed fitting, plus dub-mode voice cloning. Capability manifest (6.0): reads narration JSON, optional reference audio and env API keys; side effects confined to work_dir (tts_segments/*.wav, tts_meta.json, dub lint/review); network destinations: api.xiaomimimo.com / token-plan clusters and api.fish.audio, uploading narration text and, for cloning, reference audio — all named in the description itself, with an explicit use-only-with-authorization rule for reference audio; credentials env-only and stripped from sanitized error messages; no persistence. Capabilities match declared scope.