# Process Video, Audio, and Transcripts

Video conversion and transcription often require several command-line tools. This skill provides one CLI workflow for extracting audio, converting formats, and creating Whisper transcripts.

## Install

```bash
npx skillstore add egadams/video-processor
```

## Metadata

- Status: approved
- Slug: egadams-video-processor
- Skillstore revision: r1
- Version status: missing
- Tree hash: f5dc5651c5ee7020e266150c4e20bf3ae375cca38a9c494c1f89131121dfd1df
- Author: EGAdams
- GitHub username: EGAdams
- License: MIT
- Repository: https://github.com/EGAdams/planner/tree/main/.claude/skills/video-processor
- Ref: 30c73eac2afe762f6aa9c4553158769369d47351
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands, filesystem
- Quality score: 75
- Public page: https://skillstore.pages.dev/skills/egadams-video-processor
- Manifest: https://skillstore.pages.dev/api/skills/egadams-video-processor/manifest

## Capabilities

- Extracts audio from video files as WAV, MP3, AAC, or FLAC.
- Converts local video files to MP4 with codec, preset, and CRF options.
- Converts local video files to WebM with VP8 or VP9 settings.
- Transcribes audio or video with local Whisper models.
- Saves transcripts as TXT, SRT, VTT, or JSON files.
- Creates temporary WAV audio for video transcription and removes it after processing.

## Use Cases

- Create lecture transcripts: Extract audio from recorded classes and create text or subtitle files for review and accessibility.
- Prepare web video assets: Convert source videos to WebM and generate subtitle files for website publishing.
- Normalize media archives: Convert mixed video formats into MP4 and keep searchable transcripts beside each file.

## Prompt Templates

### Convert to MP4

```
Convert my video file to MP4 using the default quality settings. Tell me the output path when it is done.
```

### Extract clean audio

```
Extract the audio from this video as a WAV file that I can use for transcription.
```

### Create subtitles

```
Transcribe this video with the small Whisper model and save the result as an SRT subtitle file.
```

### Build a publishing workflow

```
Convert this presentation to WebM, generate an SRT transcript, and summarize the files created with their sizes.
```

## Limitations

- Requires FFmpeg, OpenAI Whisper, and Python dependencies installed locally.
- Transcription accuracy depends on model size, audio quality, and language.
- Large files and larger models can require significant CPU, memory, and time.
- Does not edit video content beyond extraction, conversion, and transcription.

## Best Practices

- Confirm the input and output paths before running commands that overwrite files.
- Use smaller Whisper models for drafts and larger models only when accuracy is more important than speed.
- Test a short clip before processing long videos or large batches.

## Anti Patterns

- Do not run conversions on untrusted media without local sandboxing or backups.
- Do not choose the large Whisper model on machines with limited memory.
- Do not assume transcripts are publication-ready without human review.

## Security Audit

- Audited at: 2026-07-05T15:08:56.882\+00:00
- Summary: The static findings are explained by intentional local media processing behavior and Markdown examples. The Python subprocess calls use fixed executable names with list arguments, and the file deletion calls clean generated temporary audio files. No prompt injection, data exfiltration, or hidden malicious behavior was found in the analyzed files.

## Stats

- Views: 158
- Downloads: 14
- Favorites: 0
- Popularity score: 0