{"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/stable-audio-open","title":"Stable Audio Open","arxiv_id":"2407.14358","date":"2024-07-19","proceeding":null,"authors":["Zach Evans","Julian D. Parker","CJ Carr","Zack Zukowski","Josiah Taylor","Jordi Pons"],"abstract":"Open generative models are vitally important for the community, allowing for fine-tunes and serving as baselines when presenting new models. However, most current text-to-audio models are private and not accessible for artists and researchers to build upon. Here we describe the architecture and training process of a new open-weights text-to-audio model trained with Creative Commons data. Our evaluation shows that the model's performance is competitive with the state-of-the-art across various metrics. Notably, the reported FDopenl3 results (measuring the realism of the generations) showcase its potential for high-quality stereo sound synthesis at 44.1kHz.","url_abs":"https://arxiv.org/abs/2407.14358v2","url_pdf":"https://arxiv.org/pdf/2407.14358v2.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":"stable-audio-open","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":"audio-generation","task_name":"Audio Generation"},{"task_slug":"text-to-music-generation","task_name":"Text-to-Music Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-generation-on-audiocaps","task":"Audio Generation","dataset":"AudioCaps","model":"Stable Audio Open","rank_in_archive_order":3,"of":23,"metrics":{"CLAP_LAION":"0.35","CLAP_MS":"0.34","FD_openl3":"78.24","KL_passt":"2.14"},"uses_additional_data":false},{"leaderboard":"/sota/text-to-music-generation-on-musiccaps","task":"Text-to-Music Generation","dataset":"MusicCaps","model":"Stable Audio Open","rank_in_archive_order":11,"of":21,"metrics":{"CLAP_LAION":"0.48","CLAP_MS":"0.49","FAD":"3.51","FD":"36.42","FD_openl3":"127.20","IS":"2.93","KL_passt":"1.32"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.14358","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.14358"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stability-ai/stable-audio-tools","reach":null}],"summary":{"ran_violates":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2c2d84ddcd7822ac","entry":"fold_channels_into_batch","repo":"stability-ai/stable-audio-tools","repo_kind":"official","path":"stable_audio_tools/models/autoencoders.py","file_url":"https://github.com/stability-ai/stable-audio-tools/blob/HEAD/stable_audio_tools/models/autoencoders.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c2d84ddcd7822ac"}},{"code_sha256_prefix":"97618fb739ec7793","entry":"checkpoint","repo":"stability-ai/stable-audio-tools","repo_kind":"official","path":"stable_audio_tools/models/autoencoders.py","file_url":"https://github.com/stability-ai/stable-audio-tools/blob/HEAD/stable_audio_tools/models/autoencoders.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"97618fb739ec7793"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}