Create a video from PNG slides with text-to-speech
Learning
Motion Controlled Video Generation
Generate spatial audio from images (and optionally text)
Generate talking face video from image and audio
Speech Enhancement Gradio Demo
Transform audio to video with AI visuals
Enhance video using convolution filters
Generate realistic audio from text input
Create photorealistic viewpoints from casual videos
Create photorealistic 3D portraits from your videos
Generate high-fidelity audio from input audio waveforms
Versatile audio super resolution (any -> 48kHz) with AudioSR
Presentation Slides VoiceOver Maker is a tool designed to transform your PNG slides into engaging videos with realistic text-to-speech voiceovers. Perfect for educators, presenters, and content creators, this tool allows you to easily add high-quality narration to your visual content, making it more impactful and accessible to your audience.
What file formats are supported?
The tool supports PNG, JPG, and other standard image formats for slides.
Can I choose different voices for different slides?
Yes, you can select different voices and languages for various slides to create a more dynamic presentation.
Is the voiceover customizable?
Absolutely! You can adjust the speed, volume, and add sound effects or music to tailor the voiceover to your needs.