2020年4月30日 · We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We’re releasing the model weights and code, along with a tool to explore the generated samples.

Browse all samples

Jukebox: A Generative Model for Music et al.,2019) to compress audio into a discrete space, with a loss function designed to retain the maximum amount of musical information, while doing so at increasing levels of compression. We use an autoregressive Sparse Trans-former (Child et al.,2019;Vaswani et al.,2017) trained with

Jukebox: A Generative Model for Audio. blog | paper | code. about

Share on Twitter | Facebook | Soundcloud | Copy link | T =

Licenses. Soundcloud; svelte; svelte-select

Explore resources, tutorials, API docs, and dynamic examples to get the most out of OpenAI's developer platform.

1,000 Scientist AI Jam Session. Global Affairs Feb 28, 2025. Stories. View all. Lyndon Barrois & Sora. Sora Dec 4, 2024 3 min read. Building a custom math tutor powered by ChatGPT. ChatGPT Feb 4, 2025 3 min read. Economics and reasoning with OpenAI o1. ChatGPT Sep 13, 2024 2 min read. Latest research.

2024年3月8日 · Hello, I’m very interested in AI music generation, and I came across OpenAI’s Jukebox and its repository on GitHub. The latest files there were updated four years ago. Does anyone know what happened to this project?

We’re also researching the best ways to help people identify when an image was created with AI. We’re experimenting with a provenance classifier—a new internal tool that can help us identify whether or not an image was generated by DALL·E 3—and hope to use this tool to better understand the ways generated images might be used.