add narration to a video automatically
v1.0.0Generate narration for silent screen-recording videos. Extracts key frames, analyzes on-screen content, writes a presentation-style voiceover script, synthes...
⭐ 0· 36·0 current·0 all-time
byRyan Zhang@ryanzhang-oss
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 match the actual artifacts: ffmpeg is needed for frame extraction/merging and python3 + edge-tts for TTS. No unrelated binaries, env vars, or config paths are requested.
Instruction Scope
SKILL.md instructs the agent to extract frames, write a script, synthesize TTS, and merge audio — all directly tied to the stated goal. The instructions do ask the user/agent to inspect frames and to ensure timing, which is expected for quality control but requires access to the extracted images and audio files.
Install Mechanism
This is instruction-only (no packaged installer). The README recommends 'pip3 install edge-tts' and installing ffmpeg via brew/apt; pip will fetch code from PyPI and execute it locally. That's expected, but installing packages from the network is a security consideration worth noting.
Credentials
No environment variables, keys, or config paths are requested. The scripts operate on local files only. There are no disproportionate credential or config demands.
Persistence & Privilege
The skill does not request persistent/always-on presence and does not modify other skills or system-wide agent settings. Scripts only create local outputs (frames, mp3, merged video).
Assessment
What to consider before installing/running: (1) The skill runs local shell scripts (extract frames, call ffmpeg, run a small Python snippet using the edge-tts package). Review those scripts (you already have them) and run in a controlled environment. (2) edge-tts is installed via pip and will fetch code from PyPI and then perform network calls to Microsoft TTS endpoints to synthesize audio — avoid feeding sensitive or private content you don't want sent to external services. (3) Ensure ffmpeg and python3 are from trusted sources on your machine; test on non-sensitive videos first. (4) If you have network egress policies, be aware the TTS step will require outbound access. (5) If you want extra caution, inspect the edge-tts package source or vendor a vetted TTS client or an on-prem TTS engine before use.Like a lobster shell, security has layers — review code before you run it.
latestvk97141nzd55rk0vdcj8s347gp1846dcx
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
🎬 Clawdis
Any binffmpeg, python3