Skillget

genpark-agentic-voice-video-ad-skill

mcp
Security Audit
Warn
Health Warn
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 9 GitHub stars
Code Pass
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Pass
  • Permissions — No dangerous permissions requested

No AI report is available for this listing yet.

SUMMARY

Agentic Voice & Video Ad creator skill designed to generate interactive voice dialogue scripts and cinematic video prompts.

README.md

Python 3.9+ License MIT MCP Compatible GenPark AI

genpark-agentic-voice-video-ad-skill

GenPark AI Agent Skill -- # Agentic Voice & Video Ad Creator Skill

This repository contains the Agentic Voice & Video Ad Creator Skill — an agent skill configuration interface (skill.json), developer SDK client (voice_video_ad.py), and validation script for generating interactive audio/voice loops (Alexa+ style) and cinematic visual scene description prompts.

🚀 Capabilities

  • Interactive Voice Assistant Flow: Generates voice dialogue loops prompting user engagement, mapping possible answers (yes, info, decline) to shopping cart transactions and assistant audio cues.
  • Cinematic Video Prompt Synthesizer: Creates descriptive, highly detailed styling instructions (lighting, angles, textures) optimized for AI video models (Runway Gen-3, Grok Imagine, Sora).
  • Atmospheric Cohesion: Automatically aligns visual prompts and voice scripts with a defined campaign mood (e.g. futuristic, comfort, luxury).

🛠️ Setup & Installation

  1. Install dependencies:

    pip install -r requirements.txt

  2. Configuration:
    Set your API environment variables if executing requests against the live production server (otherwise, client executes in mock mode):

    • PowerShell:
      $env:AD_CREATOR_API_KEY="your_api_key"
    • bash:
      export AD_CREATOR_API_KEY="your_api_key"

💻 SDK Usage Reference

from voice_video_ad import VoiceVideoAdClient

# Initialize Client (mock mode by default)
client = VoiceVideoAdClient()

# Generate Alexa+ style voice script
voice = client.generate_interactive_script(
    product_name="Zenith Speaker",
    pitch="Great sound.",
    mood="futuristic"
)
print(voice["voice_script"])
print(voice["user_replies_mapped"])

# Generate cinematic video scene prompts
prompts = client.generate_video_prompts(
    product_name="Zenith Speaker",
    mood="futuristic"
)
print(prompts[0]["visual_prompt"])

📜 License

This project is licensed under the MIT License.

📊 Agentic Architecture Flowchart

graph LR
  User([User / AI Agent]) -->|JSON Request| Skill[GenPark AI Skill]
  Skill -->|Execution Logic| CoreEngine[Core Analytics & Processing]
  CoreEngine -->|Structured Output| User

🔌 MCP (Model Context Protocol) Integration

Run natively as an MCP server for Cursor, Claude Desktop & LLM frameworks:

python mcp_server.py

Reviews (0)

No results found