{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-text-to-audio-generation-with","title":"Fast Text-to-Audio Generation with Adversarial Post-Training","arxiv_id":"2505.08175","date":"2025-05-13","proceeding":null,"authors":["Zachary Novack","Zach Evans","Zack Zukowski","Josiah Taylor","CJ Carr","Julian Parker","Adnan Al-Sinan","Gian Marco Iodice","Julian McAuley","Taylor Berg-Kirkpatrick","Jordi Pons"],"abstract":"Text-to-audio systems, while increasingly performant, are slow at inference time, thus making their latency unpractical for many creative applications. We present Adversarial Relativistic-Contrastive (ARC) post-training, the first adversarial acceleration algorithm for diffusion/flow models not based on distillation. While past adversarial post-training methods have struggled to compare against their expensive distillation counterparts, ARC post-training is a simple procedure that (1) extends a recent relativistic adversarial formulation to diffusion/flow post-training and (2) combines it with a novel contrastive discriminator objective to encourage better prompt adherence. We pair ARC post-training with a number optimizations to Stable Audio Open and build a model capable of generating $\\approx$12s of 44.1kHz stereo audio in $\\approx$75ms on an H100, and $\\approx$7s on a mobile edge-device, the fastest text-to-audio model to our knowledge.","url_abs":"https://arxiv.org/abs/2505.08175v3","url_pdf":"https://arxiv.org/pdf/2505.08175v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-text-to-audio-generation-with","repo_url":"https://github.com/stability-ai/stable-audio-tools","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"arc","task_name":"ARC"},{"task_slug":"audio-generation","task_name":"Audio Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.08175","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}