ClawVid

Generate short-form videos from text prompts using AI narration, visuals, and audio.

22|1|Updated Feb 11, 2026
One-click install
npx skills add https://github.com/neur0map/clawvid --skill clawvid
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ClawVid
Source: https://github.com/neur0map/clawvid/tree/main
Command: npx skills add https://github.com/neur0map/clawvid --skill clawvid

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires @fal-ai/client, @remotion/bundler, @remotion/cli, @remotion/renderer, chalk, cli-progress, commander, dotenv, file-type, fluent-ffmpeg, fs-extra, nanoid, ora, p-queue, p-retry, pino, remotion, sharp, zod, and includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the creation of short-form videos for platforms like YouTube Shorts, TikTok, and Instagram Reels directly from text prompts, streamlining the entire video production pipeline.

Core Features & Use Cases

  • End-to-End Video Generation: From text prompts to final rendered video, including AI-generated narration, visuals, sound effects, and music.
  • TTS-Driven Timing: Ensures video pacing perfectly matches the generated narration length for natural flow.
  • Visual Consistency: Maintains character and style consistency across scenes using advanced AI techniques.
  • Use Case: Generate a 30-second horror video about a haunted library from a simple text description, complete with custom narration, spooky visuals, sound effects, and background music.

Quick Start

Use the clawvid skill to generate a video from the workflow file 'workflows/horror-story-example.json'.

Frequently Asked Questions about ClawVid

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

FAQPage Schema
How do I generate short-form videos for TikTok and YouTube Shorts from text prompts?

Short-form video generation from text prompts is automated by orchestrating AI models for narration, visuals, and audio via a workflow JSON, directly outputting platform-specific formats for TikTok and YouTube Shorts.

How does TTS-driven timing sync narration with AI video generation?

TTS-driven timing ensures the video pacing perfectly matches the generated narration length. This mechanism creates a natural flow by aligning visual transitions and scene changes directly with the AI-generated audio duration.

Can I maintain visual consistency across scenes when generating AI videos?

Visual consistency across scenes is maintained by providing reference images to the AI generation workflow. This ensures characters and styles remain uniform throughout the final rendered video.

Do I need fal.ai and Remotion to automate video production pipelines?

Yes, the pipeline integrates with fal.ai for AI generation and Remotion for composition. These dependencies are required to handle the automated rendering, visual orchestration, and final video output.

What is the best way to add custom sound effects and background music to AI video?

The best way to add custom audio is by defining it within the workflow JSON before rendering. The pipeline automatically generates and integrates sound effects and background music alongside the AI visuals and TTS narration.

Are there limitations when using reference images for character consistency in Remotion?

Limitations depend on the fal.ai model's ability to interpret reference images accurately within the JSON workflow. While Remotion handles the final composition, any visual inconsistencies usually originate from the underlying AI generation constraints.