https://github.com/alecrust/tube-crafter

Generate a video from a topic using AI.
https://github.com/alecrust/tube-crafter

ai openai text-to-speech video-creation

Last synced: about 24 hours ago
JSON representation

Generate a video from a topic using AI.

• Host: GitHub
• URL: https://github.com/alecrust/tube-crafter
• Owner: AlecRust
• Created: 2023-08-04T18:58:52.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-11-01T16:15:46.000Z (over 1 year ago)
• Last Synced: 2025-01-17T22:22:29.114Z (about 1 month ago)
• Topics: ai, openai, text-to-speech, video-creation
• Language: JavaScript
• Homepage: https://npm.im/tube-crafter
• Size: 540 KB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# tube-crafter [![CI](https://github.com/AlecRust/tube-crafter/actions/workflows/ci.yml/badge.svg)](https://github.com/AlecRust/tube-crafter/actions/workflows/ci.yml) [![npm version](https://img.shields.io/npm/v/tube-crafter.svg)](https://www.npmjs.com/package/tube-crafter)

Generate a video from a topic, or a script you already have.

## Installation

```sh

npm install -g tube-crafter

```

## Prerequisites

- [ffmpeg](https://ffmpeg.org/) must be installed

- `OPENAI_API_KEY` must be set in your environment

- Your machine must be able to access Google Cloud ([instructions](https://github.com/googleapis/google-cloud-node/tree/main/packages/google-cloud-texttospeech#quickstart))

## Usage

```sh

tube-crafter --topic "red squirrels"

tube-crafter --script my-script.md

```

When you run the command it will create an `output` directory in the current directory, and a timestamped directory inside for each run. The final video is located at e.g. `output/2023-08-18T11-33-06-013Z/output.mp4`.

## How it works

1. Creates a video script from the topic provided (or uses provided script)

2. Splits the script into "text lines" (paragraphs and headings)

3. Creates a text-to-speech MP3 for each text line

4. Creates an image for each text line (if heading, text shown in image)

5. Creates a video for each text line (using the MP3 and image)

6. Concatenates all the videos into a single video