Text To Video AI

Generate engaging videos from text prompts using AI. Perfect for creating YouTube Shorts, Instagram Reels, TikTok videos, and more.

Want to skip the setup? Use our Premium API to generate videos instantly - no installation required, production-ready, and scales with your needs.

▶ Watch: Best AI Video Generator (API) in 2026 (Quality, Price, Uncensored, Editing)

Demo

https://github.com/user-attachments/assets/1e440ace-8560-4e12-850e-c532740711e7

Sample Videos

Here are sample videos generated end-to-end directly by this project using the React/Remotion composition engine:

"Wonders of Outer Space" — An educational video about the cosmos, galaxies, and black holes. Generated using local EdgeTTS voiceover, whisper-timestamped local word captions, Suno AI background music, and Veo3 AI B-roll video segments.

"Exploring the Deep Ocean" — A cinematic short exploring deep sea depths, bioluminescent creatures, and thermal vents. Generated using local EdgeTTS voiceover, whisper-timestamped local word captions, Suno AI background music, and Veo3 AI B-roll video segments.

Features

• AI-Powered Script Generation - Automatically generates engaging scripts from any topic
• Multiple LLM Providers - Choose from OpenAI, Groq, or Google Gemini
• Text-to-Speech - Natural-sounding voiceovers with EdgeTTS (free) or ElevenLabs
• Automatic B-Roll - Fetches relevant background videos from Pexels
• Customizable Captions - Full control over font, color, position, and styling
• Multiple Orientations - Portrait (9:16) for shorts or Landscape (16:9) for traditional video
• Speech-to-Text - Accurate caption timing with Whisper or Deepgram

Quick Start

Option 1: Use the Premium API (Recommended)

Skip all setup and generate videos with a single API call:

• Premium API Documentation

Option 2: Google Colab

Run directly in your browser with our Colab Notebook

Option 3: Local Installation

See installation instructions below.

Installation

Prerequisites

• Python 3.8+
• FFmpeg
• ImageMagick

Windows users: See INSTALL_WINDOWS.md for detailed setup instructions.

Setup

# Clone the repository
git clone https://github.com/SamurAIGPT/Text-To-Video-AI.git
cd Text-To-Video-AI

# Install dependencies
pip install -r requirements.txt

# Create your configuration file
cp .env.example .env

Edit .env with your API keys (see Configuration below).

Usage

python app.py "Your topic here"

Output will be saved as rendered_video.mp4

Configuration

All settings are configured via the .env file. Copy .env.example to get started.

API Keys

Provider Selection

# LLM Provider: openai, groq, or gemini
LLM_PROVIDER=openai

# Text-to-Speech: edgetts (free) or elevenlabs
TTS_PROVIDER=edgetts

# Speech-to-Text: whisper (free) or deepgram
STT_PROVIDER=whisper

Video Settings

# Orientation: portrait (1080x1920) or landscape (1920x1080)
# Portrait recommended for YouTube Shorts, Instagram Reels, TikTok
VIDEO_ORIENTATION=portrait

AI Video Generation (Muapi)

# Muapi API credentials
MUAPI_BASE_URL=https://api.muapi.ai
MUAPI_API_KEY=your_key

# Video Model to use
MUAPI_VIDEO_MODEL=veo3-fast-text-to-video

Supported Muapi Video Models:

• Google Veo: veo3-fast-text-to-video, veo3-text-to-video, veo3.1-fast-text-to-video, veo3.1-text-to-video, veo3.1-lite-text-to-video
• xAI Grok: grok-imagine-text-to-video
• ByteDance Seedance: sd-2-t2v (Seedance 2), seedance-2-vip-text-to-video, seedance-pro-t2v, seedance-lite-t2v
• Wan: wan2.7-text-to-video, wan2.6-text-to-video, wan2.5-text-to-video, wan2.1-text-to-video
• LTX: ltx-2.3-text-to-video, ltx-2-pro-text-to-video, ltx-2-fast-text-to-video
• Kling: kling-v3.0-pro-text-to-video, kling-v3.0-standard-text-to-video
• Vidu: vidu-q3-pro-text-to-video, vidu-q2-pro-text-to-video
• OpenAI Sora: openai-sora-2-pro-text-to-video, openai-sora-2-standard-text-to-video
• MiniMax: minimax-hailuo-2.3-pro-t2v, minimax-hailuo-2.3-standard-t2v
• Alibaba: happy-horse-1-text-to-video-1080p

Caption Settings

# Enable or disable captions
CAPTIONS_ENABLED=true

# Caption styling
CAPTION_FONT_SIZE=100
CAPTION_FONT_COLOR=white
CAPTION_FONT_FACE=Arial-Bold
CAPTION_STROKE_WIDTH=3
CAPTION_STROKE_COLOR=black
CAPTION_POSITION=bottom_center

Caption Position Options: center, top, bottom, bottom_center, bottom_left, bottom_right

Font Color Options: white, yellow, cyan, red, green, blue, magenta

Voice Configuration

EdgeTTS (Free):

EDGETTS_VOICE=en-AU-WilliamNeural

Popular voices:

• en-US-ChristopherNeural - American male
• en-US-JennyNeural - American female
• en-GB-RyanNeural - British male
• en-GB-SoniaNeural - British female
• en-AU-WilliamNeural - Australian male

ElevenLabs:

ELEVENLABS_API_KEY=your_key
ELEVENLABS_VOICE_ID=your_voice_id

Tutorials

• YouTube Tutorial
• Medium Guide

Contributing

We welcome contributions! To get started:

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

---

Premium API

Looking for a production-ready solution? Our Premium API offers:

• No installation or setup required
• Multiple video durations (30s to 10 minutes)
• Advanced voice and language options
• Custom styling and branding
• Scalable infrastructure

Get Started with the API

---

Related Projects

• MuAPI video-generation docs — API patterns for text-to-video generation.
• Veo 3 text-to-video playground — Try a production video model in the browser.

• awesome-ai-video-models — compare AI video models by API, price & speed
• ai-creator-academy — free curriculum teaching creators how to monetize AI-generated video content

Vadoo AI Tools

• AI Video Generator
• Text to Video AI
• Autoshorts AI
• Pixverse Alternative
• Hailuo AI Alternative
• Minimax AI Alternative

---

Support

If you find this project useful, please consider giving it a star! Your support helps us continue improving the project.