Audio Gen, Audio Style Transfer and Audio InPainting
Image + Audio = Animated Video [Talking Head Animations]
Generate a long video from an image with effects
Generate spatial audio from images (and optionally text)
Video-Subtitle-Generator
Transform casual videos into photorealistic 3D portraits
Generate sound for silent videos
Create a video from PNG slides with text-to-speech
Select the more realistic video from pairs
Audio Conditioned LipSync with Latent Diffusion Models
Speech Enhancement Gradio Demo
Versatile audio super resolution (any -> 48kHz) with AudioSR
Generate lip-synced video using audio
Auffusion is an AI-powered tool designed to add realistic sound to videos. It offers advanced features like Audio Generation, Audio Style Transfer, and Audio InPainting, allowing users to create immersive audio experiences. Whether you need to generate audio from text prompts or reference existing audio, Auffusion provides a flexible solution for enhancing video content.
• Audio Generation: Create realistic audio from text prompts or audio references, perfect for adding sound effects, voices, or ambient noise to videos. • Audio Style Transfer: Transfer the style of one audio clip to another, enabling unique soundscapes and creative audio transformations. • Audio InPainting: Precisely edit and refine audio by removing or replacing specific parts, ensuring seamless integration with video content.
What types of audio can Auffusion generate?
Auffusion can generate a wide range of audio, including sound effects, voices, and ambient noise, based on text prompts or audio references.
Can I customize the output audio?
Yes, Auffusion allows you to adjust settings like pitch, speed, and intensity to customize the output audio to your preferences.
Where can I access Auffusion?
Auffusion is available as a web-based application, and you can access it directly through your browser for seamless video and audio enhancement.