Hacker News with Generative AI: Audio Generation

Video-Guided Foley Sound Generation with Multimodal Controls (ificl.github.io)
Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design.
Video Editing, Artificial Intelligence, Sound Design, Audio Generation
46 points by surprisetalk 84 days ago | 19 comments
Nvidia claims a new AI audio generator can make sounds never heard before (theverge.com)
Nvidia says its new AI music editor can create “sounds never heard before” — like a trumpet that meows. The tool, called Fugatto, is capable of generating music, sounds, and speech using text and audio inputs it’s never been trained on.
Artificial Intelligence, Music, Technology, Audio Generation
11 points by jnord 87 days ago | 3 comments
Show HN: PlayNote – NotebookLM but with custom voices and API (play.ai)
Turn your files and data into captivating audio creations. Enjoy cutting-edge AI voice synthesis.
AI, Audio Generation, Voice Synthesis, Software, New Releases
18 points by amrrs 100 days ago | 4 comments
Pushing the frontiers of audio generation (deepmind.google)
Our pioneering speech generation technologies are helping people around the world interact with more natural, conversational and intuitive digital assistants and AI tools.
Audio Generation, Artificial Intelligence, Speech Technology
237 points by meetpateltech 113 days ago | 107 comments
Amphion: An open-source audio, music, and speech generation toolkit (github.com/open-mmlab)
Amphion (/æmˈfaɪən/) is a toolkit for Audio, Music, and Speech Generation. Its purpose is to support reproducible research and help junior researchers and engineers get started in the field of audio, music, and speech generation research and development.
Audio Generation, Open Source, Music Generation, Speech Generation, Research
92 points by lapnect 116 days ago | 2 comments
EzAudio: Enhancing Text-to-Audio Generation with Efficient Diffusion Transformer (haidog-yaqub.github.io)
EzAudio is an advanced text-to-audio (T2A) generation model that creates high-quality audio from text prompts. It sets a new standard for open-source T2A models by delivering fast, efficient, and realistic sound effects generation.
Text-to-Audio, Audio Generation, Open Source, Artificial Intelligence, Machine Learning
99 points by blacktechnology 150 days ago | 17 comments
Generating audio for video: using video and text prompts to generate soundtracks (deepmind.google)
Generative AI, Audio Generation, Video, Machine Learning, Deep Learning
18 points by skoppula 247 days ago | 2 comments