muapi-animal-video-generator

Generates anthropomorphic animal vlogger videos using MuAPI image and video models.

4.2k|481|Updated May 25, 2023
One-click install
npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-animal-video-generator
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: muapi-animal-video-generator
Source: https://github.com/SamurAIGPT/Generative-Media-Skills/tree/main/library/motion/animal-video-generator
Command: npx skills add https://github.com/SamurAIGPT/Generative-Media-Skills --skill muapi-animal-video-generator

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Creating a realistic talking-animal vlog video normally requires filming, animation, and lip-sync expertise. This Skill orchestrates a two-phase pipeline that turns a simple text idea into a finished vertical video of an animal vlogger speaking custom dialogue.

Core Features & Use Cases

  • Two-Phase Generation: First creates a photorealistic base image of the animal vlogger with nano-banana, then animates it with lip-synced speech using veo3.1-fast-image-to-video.
  • Customizable Inputs: Configure the animal type, location, clothing, and dialogue script through simple text parameters with sensible defaults.
  • Vertical Vlog Format: Produces 9:16 aspect ratio output suited for short-form social media platforms.
  • Use Case: A content creator wants a funny video of a monkey in a red t-shirt complaining about the heat while vlogging on the streets of Noida — they provide the script and receive a lip-synced vertical video.

Quick Start

Ask the agent to create an animal vlogger video of a monkey wearing a red t-shirt vlogging on the busy streets of Noida with your chosen dialogue.

Frequently Asked Questions about muapi-animal-video-generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a talking animal video with AI?

Provide an animal type, location, clothing, and dialogue script. The skill first generates a photorealistic image of the animal vlogger with nano-banana, then animates it with lip-synced speech using the veo3.1-fast-image-to-video model via the muapi CLI.

How to generate an image and animate it into a video with MuAPI?

Run muapi image generate with the nano-banana model to create the base image, then pass that image to muapi video from-image with the veo3.1-fast-image-to-video model and a motion prompt. The skill automates this two-phase sequence.

What inputs can I customize in the animal vlogger video?

You can set four optional text inputs: animal_type (default monkey), location (default busy streets of Noida, India), clothing (default a bright red t-shirt), and script, which is the dialogue used for lip-sync.

Does the animal video support custom dialogue and lip-sync?

Yes, the script input is passed as dialogue for lip-sync during the video generation phase when the model supports audio. The default script is a Hindi monologue, but any language text can be substituted.

What do I need before running this video generation skill?

You need the muapi CLI installed and a valid MUAPI_API_KEY configured via muapi auth configure. If a model lacks a CLI alias, the skill falls back to direct curl calls against the MuAPI REST endpoint.