# Send Video Editing Agent (VEA) to your agent
Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.
## Fast path
- Download the package from Yavira.
- Extract it into a folder your agent can access.
- Paste one of the prompts below and point your agent at the extracted folder.
## Suggested prompts
### New install

```text
I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete.
```
### Upgrade existing

```text
I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run.
```
## Machine-readable fields
```json
{
  "schemaVersion": "1.0",
  "item": {
    "slug": "vea",
    "name": "Video Editing Agent (VEA)",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/shawnshenopeninterx/vea",
    "canonicalUrl": "https://clawhub.ai/shawnshenopeninterx/vea",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadUrl": "/downloads/vea",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vea",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "packageFormat": "ZIP package",
    "primaryDoc": "SKILL.md",
    "includedAssets": [
      "SKILL.md",
      "references/api.md",
      "references/config.md",
      "scripts/add_music.sh",
      "scripts/start_server.sh",
      "scripts/vea_helper.sh"
    ],
    "downloadMode": "redirect",
    "sourceHealth": {
      "source": "tencent",
      "slug": "vea",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-04T09:09:40.616Z",
      "expiresAt": "2026-05-11T09:09:40.616Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vea",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vea",
        "contentDisposition": "attachment; filename=\"vea-1.1.2.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "vea"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/vea"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    }
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/vea",
    "downloadUrl": "https://openagent3.xyz/downloads/vea",
    "agentUrl": "https://openagent3.xyz/skills/vea/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vea/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vea/agent.md"
  }
}
```
## Documentation

### Installation

VEA is open source! Get it from GitHub:

# Clone the repo
git clone https://github.com/Memories-ai-labs/vea-open-source.git
cd vea-open-source

# Install uv package manager
curl -LsSf https://astral.sh/uv/install.sh | sh

# Install dependencies
uv sync
source .venv/bin/activate

# Copy config and add your API keys
cp config.example.json config.json

📄 Paper: https://arxiv.org/abs/2509.16811
💻 Code: https://github.com/Memories-ai-labs/vea-open-source

### Requirements

Python 3.11+
FFmpeg - Must be installed on system
uv - Package manager (installed above)
API Keys (in config.json):

MEMORIES_API_KEY (required) - Video indexing & comprehension - Get at https://memories.ai/app/service/key
GOOGLE_API_KEY (required) - Script generation - Google Cloud Console
ELEVENLABS_API_KEY (required) - TTS narration & subtitles
SOUNDSTRIPE_KEY (optional) - Background music selection

### Install FFmpeg

OSCommandUbuntu/Debiansudo apt install ffmpegmacOSbrew install ffmpegWindowsDownload from ffmpeg.org

### Start Server

gcloud auth application-default login  # Authenticate GCP
source .venv/bin/activate
python -m src.app

Server runs at http://localhost:8000

### Privacy Note

Videos processed locally by VEA server
Video frames sent to Memories.ai for AI comprehension
ElevenLabs receives text for TTS narration
All intermediate files stored locally in data/outputs/

### Video Editing Agent (VEA)

Local video editing service at http://localhost:8000. Runs from ~/vea.

### ⚠️ User Interaction Flow (MUST FOLLOW)

Before processing any video edit request, show config options and wait for confirmation:

📹 VEA Video Edit Configuration

🎬 Source Video: [video path/name]
📝 Edit Request: [user's prompt]

Please confirm the following settings:
┌─────────────────┬────────┬─────────────────────────┐
│ Setting         │ Value  │ Description             │
├─────────────────┼────────┼─────────────────────────┤
│ 🔊 Original Audio        │ ❌ OFF │ Keep original video sound    │
│ 🎤 Narration             │ ✅ ON  │ AI-generated voiceover       │
│ 🎵 Background Music      │ ✅ ON  │ Auto-select from Soundstripe │
│ 📝 Subtitles             │ ✅ ON  │ Auto-generate and burn-in    │
│ 📐 Aspect Ratio          │ 16:9   │ 16:9 / 9:16 vertical / 1:1   │
│ 🎼 Snap to Beat          │ ❌ OFF │ Sync cuts to music beats     │
└─────────────────┴────────┴─────────────────────────┘

Reply "confirm" to start editing, or tell me which settings to adjust.

Default Settings:

original_audio: false (mute original, use narration instead)
narration: true (enable AI voiceover)
music: true (enable background music)
subtitles: true (enable subtitles)
aspect_ratio: 1.78 (16:9 landscape)
snap_to_beat: false (no beat sync)

Aspect Ratio Options:

16:9 (1.78) — Landscape, YouTube
9:16 (0.5625) — Vertical, TikTok/Reels
1:1 (1.0) — Square, Instagram

### Quick Start

# Start VEA server (use tmux for long tasks)
cd ~/vea && source .venv/bin/activate && python src/app.py

### 1. Index a Video (Required First Step)

Before any editing, index the video to enable AI comprehension:

curl -X POST "http://localhost:8000/video-edit/v1/index" \\
  -H "Content-Type: application/json" \\
  -d '{"blob_path": "data/videos/PROJECT_NAME/video.mp4"}'

Creates ~/vea/data/indexing/PROJECT_NAME/media_indexing.json.

### 2. Generate Highlight Reel

curl -X POST "http://localhost:8000/video-edit/v1/flexible_respond" \\
  -H "Content-Type: application/json" \\
  -d '{
    "blob_path": "data/videos/PROJECT_NAME/video.mp4",
    "prompt": "Create a 1-minute highlight reel of the best moments",
    "video_response": true,
    "original_audio": false,
    "music": true,
    "narration": true,
    "aspect_ratio": 1.78,
    "subtitles": true
  }'

Parameters:

video_response: true — Generate video output (vs text-only)
original_audio: false — Mute original audio, use narration
music: true — Add background music (requires Soundstripe API)
narration: true — Generate AI voiceover (ElevenLabs)
subtitles: true — Burn subtitles into video
aspect_ratio — 1.78 (16:9), 1.0 (square), 0.5625 (9:16 vertical)

### 3. Manual Video Assembly

For more control, use the helper scripts:

# Add background music to existing video
python ~/vea/scripts/add_soundstripe_music.py

# Generate video with subtitles
python ~/vea/scripts/add_music_subtitles.py

### Directory Structure

~/vea/
├── data/
│   ├── videos/PROJECT_NAME/      # Source videos
│   ├── indexing/PROJECT_NAME/    # media_indexing.json
│   └── outputs/PROJECT_NAME/     # Final outputs
│       ├── PROJECT_NAME.mp4      # Final video
│       ├── clip_plan.json        # Clip timestamps + narration
│       ├── narrations/           # TTS audio files
│       ├── subtitles/            # SRT files
│       └── music/                # Background music
├── config.json                   # API keys configuration
└── src/app.py                    # FastAPI server

### API Keys (in config.json)

KeyServicePurposeRequiredMEMORIES_API_KEYMemories.aiVideo indexing & comprehension✅ YesGOOGLE_API_KEYGeminiScript generation✅ YesELEVENLABS_API_KEYElevenLabsTTS narration, STT subtitles✅ YesSOUNDSTRIPE_KEYSoundstripeBackground music selectionOptional

### Common Issues

"ViNet assets not found" — Dynamic cropping disabled. Set enable_dynamic_cropping: false in config.json.

Subprocess fails from API but works manually — Run server in tmux to preserve environment.

Music download 401/403 — Check Soundstripe API key validity.

Clip timestamps wrong — Ensure original_audio: true to enable timestamp refinement via transcription.

### Manual Music Addition

When Soundstripe fails, manually download and mix:

# Download from Soundstripe API
SOUNDSTRIPE_KEY=$(jq -r '.api_keys.SOUNDSTRIPE_KEY' ~/vea/config.json)
curl -s "https://api.soundstripe.com/v1/songs/TRACK_ID" \\
  -H "Authorization: Token $SOUNDSTRIPE_KEY" | jq '.included[0].attributes.versions.mp3'

# Mix with ffmpeg (15-20% music volume)
ffmpeg -y -i video.mp4 -i music.mp3 \\
  -filter_complex "[1:a]volume=0.18,afade=t=out:st=70:d=4[m];[0:a][m]amix=inputs=2:duration=first[a]" \\
  -map 0:v -map "[a]" -c:v copy -c:a aac output.mp4

### References

API Documentation — Full endpoint specs
Config Schema — Configuration options
## Trust
- Source: tencent
- Verification: Indexed source record
- Publisher: shawnshenopeninterx
- Version: 1.1.2
## Source health
- Status: healthy
- Item download looks usable.
- Yavira can redirect you to the upstream package for this item.
- Health scope: item
- Reason: direct_download_ok
- Checked at: 2026-05-04T09:09:40.616Z
- Expires at: 2026-05-11T09:09:40.616Z
- Recommended action: Download for OpenClaw
## Links
- [Detail page](https://openagent3.xyz/skills/vea)
- [Send to Agent page](https://openagent3.xyz/skills/vea/agent)
- [JSON manifest](https://openagent3.xyz/skills/vea/agent.json)
- [Markdown brief](https://openagent3.xyz/skills/vea/agent.md)
- [Download page](https://openagent3.xyz/downloads/vea)