slide-to-video-converter
v1.0.0End-to-end pipeline for converting PPT/PPTX/PDF slides with speaker notes into narrated MP4 videos. Defaults to Edge TTS (Microsoft free online API) for univ...
⭐ 0· 62·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
The name/description (slide → narrated video) matches the included scripts (PDF/PPTX→images, TTS, per-slide composition, merge). Requested system commands (ffmpeg, libreoffice, poppler) and Python packages are appropriate for the described work. No unrelated binaries, env vars, or config paths are required.
Instruction Scope
SKILL.md and scripts operate on local slide files (slides/presentation.pdf or .pptx), a subtitles JSON, and assets/config.json. They do perform network I/O for TTS: default Edge TTS uses an online Microsoft endpoint via the edge-tts package, and the HTTP mode will POST the text payload to whatever _tts_http_url you configure. This network behavior is expected by the skill but is a privacy consideration (your slide text will be transmitted).
Install Mechanism
No automated install spec is provided (instruction-only). Dependencies are installed via common package managers and pip as documented. The 'direct' Qwen3-TTS mode implies large local model loading and native GPU/metal compilation steps (expected for local TTS). There are no downloads from obscure URLs in the install instructions.
Credentials
The skill declares no required environment variables or credentials, which is consistent. However: (1) Edge TTS transmits text to Microsoft's online service (edge-tts) without an API key by design; (2) HTTP mode will send JSON containing the slide text to the configured HTTP server (default localhost:8100, but can be set to any host). If you set the HTTP URL to an external server, you will be sending content externally. These behaviors are expected but important to consider.
Persistence & Privilege
The skill does not request 'always: true' and does not appear to modify other skills or system-wide agent settings. It creates/uses local output directories under the project (output/images, output/audio, output/video) which is normal for a pipeline of this type.
Assessment
This skill appears to do what it claims: convert PPT/PPTX/PDF + JSON speaker notes into narrated MP4s. Before installing/running, consider:
- Privacy: default Edge TTS will send your slide text to Microsoft's online service; the HTTP TTS option will POST slide text to whatever server you configure. If your slides contain sensitive information, avoid Edge/HTTP modes or point the HTTP mode at a trusted local server.
- Offline use: the 'direct' Qwen3-TTS mode loads a local model which may require large downloads and GPU/Metal compilation; expect heavy resource use and follow tts_server.py's instructions.
- Dependencies & system tools: you must install ffmpeg, poppler, and (for PPTX→PDF) libreoffice; the pipeline uses subprocess to invoke these tools. Run inside a controlled environment (virtualenv, container) if you have security or reproducibility concerns.
- Review tts_server.py if you plan to run the included HTTP server or point to a remote HTTP TTS endpoint; verify it doesn't expose unintended network interfaces.
If you understand the data-flow (local files → optional network TTS) and are comfortable with dependencies and privacy trade-offs, the skill is coherent and reasonable to use.Like a lobster shell, security has layers — review code before you run it.
latestvk97afxw5xv1vfk70nk2we0yf3583hjqv
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
