AI Video Creator Tool
Budget: ₹12,500 – ₹37,500 INR
I want to build a small AI-powered tool that lets me generate short, engaging videos ready for Instagram Reels and YouTube Shorts. The focus is on social media posts—not long-form content or ads—so speed and ease of use come first.
Here’s what the finished tool must do:
• Automatic video editing: drop in raw clips or images and have the system cut, trim, add basic transitions, and arrange everything to a preset length (15-60 seconds) without manual timelines.
• Customizable templates: branded frames, fonts, colors, and ratio presets (9:16 vertical by default) that I can tweak once and reuse.
• Text-to-speech functionality: type or paste a script and have a natural-sounding voiceover generated and synced to the visuals.
Workflow I picture:
1. Upload media and/or script.
2. Choose a template.
3. Let the AI assemble, overlay captions, generate TTS, and export a ready-to-post vertical MP4.
4. Download or push straight to Instagram and YouTube.
I’m open to Python, Node, or any stack you’re comfortable with, as long as it runs on a standard cloud VM and has a simple web interface. Please plan for clearly commented source code and a brief setup guide so I can host it myself.
When you reply, let me know:
• Which AI video or TTS libraries you propose (e.g., ffmpeg, OpenAI, ElevenLabs, etc.).
• A rough milestone breakdown from prototype to polished UI.
• Any similar tools you’ve already built.
I’m aiming for a lightweight, dependable solution that I can start using quickly and improve over time.
Here’s what the finished tool must do:
• Automatic video editing: drop in raw clips or images and have the system cut, trim, add basic transitions, and arrange everything to a preset length (15-60 seconds) without manual timelines.
• Customizable templates: branded frames, fonts, colors, and ratio presets (9:16 vertical by default) that I can tweak once and reuse.
• Text-to-speech functionality: type or paste a script and have a natural-sounding voiceover generated and synced to the visuals.
Workflow I picture:
1. Upload media and/or script.
2. Choose a template.
3. Let the AI assemble, overlay captions, generate TTS, and export a ready-to-post vertical MP4.
4. Download or push straight to Instagram and YouTube.
I’m open to Python, Node, or any stack you’re comfortable with, as long as it runs on a standard cloud VM and has a simple web interface. Please plan for clearly commented source code and a brief setup guide so I can host it myself.
When you reply, let me know:
• Which AI video or TTS libraries you propose (e.g., ffmpeg, OpenAI, ElevenLabs, etc.).
• A rough milestone breakdown from prototype to polished UI.
• Any similar tools you’ve already built.
I’m aiming for a lightweight, dependable solution that I can start using quickly and improve over time.