{"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/soundstorm-efficient-parallel-audio","title":"SoundStorm: Efficient Parallel Audio Generation","arxiv_id":"2305.09636","date":"2023-05-16","proceeding":null,"authors":["Zalán Borsos","Matt Sharifi","Damien Vincent","Eugene Kharitonov","Neil Zeghidour","Marco Tagliasacchi"],"abstract":"We present SoundStorm, a model for efficient, non-autoregressive audio generation. SoundStorm receives as input the semantic tokens of AudioLM, and relies on bidirectional attention and confidence-based parallel decoding to generate the tokens of a neural audio codec. Compared to the autoregressive generation approach of AudioLM, our model produces audio of the same quality and with higher consistency in voice and acoustic conditions, while being two orders of magnitude faster. SoundStorm generates 30 seconds of audio in 0.5 seconds on a TPU-v4. We demonstrate the ability of our model to scale audio generation to longer sequences by synthesizing high-quality, natural dialogue segments, given a transcript annotated with speaker turns and a short prompt with the speakers' voices.","url_abs":"https://arxiv.org/abs/2305.09636v1","url_pdf":"https://arxiv.org/pdf/2305.09636v1.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":"soundstorm-efficient-parallel-audio","repo_url":"https://github.com/ZhangXInFD/soundstorm-speechtokenizer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soundstorm-efficient-parallel-audio","repo_url":"https://github.com/lucidrains/soundstorm-pytorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"soundstorm-efficient-parallel-audio","repo_url":"https://github.com/nari-labs/dia","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"audio-generation","task_name":"Audio Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.09636","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.09636"}},"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/lucidrains/soundstorm-pytorch","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ZhangXInFD/soundstorm-speechtokenizer","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nari-labs/dia","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_violates":4,"ran_honours":1,"ran":1,"unverified":5},"by_repo_kind":{"listed":{"samples":8,"ran":3,"repositories":2}},"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":3,"samples":[{"code_sha256_prefix":"856d86b39c6005b4","entry":"divisible_by","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"856d86b39c6005b4"}},{"code_sha256_prefix":"5cfcc1d3230706ff","entry":"cast_tuple","repo":"lucidrains/soundstorm-pytorch","repo_kind":"listed","path":"soundstorm_pytorch/trainer.py","file_url":"https://github.com/lucidrains/soundstorm-pytorch/blob/HEAD/soundstorm_pytorch/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5cfcc1d3230706ff"}},{"code_sha256_prefix":"60fff7c3c400d7ff","entry":"default","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"60fff7c3c400d7ff"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"1ff4da2e5b7c8f30","entry":"xnor","repo":"lucidrains/soundstorm-pytorch","repo_kind":"listed","path":"soundstorm_pytorch/soundstorm.py","file_url":"https://github.com/lucidrains/soundstorm-pytorch/blob/HEAD/soundstorm_pytorch/soundstorm.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1ff4da2e5b7c8f30"}},{"code_sha256_prefix":"d95562c398a6b25e","entry":"yes_or_no","repo":"lucidrains/soundstorm-pytorch","repo_kind":"listed","path":"soundstorm_pytorch/trainer.py","file_url":"https://github.com/lucidrains/soundstorm-pytorch/blob/HEAD/soundstorm_pytorch/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d95562c398a6b25e"}},{"code_sha256_prefix":"bd5b74f128417448","entry":"apply_audio_delay","repo":"nari-labs/dia","repo_kind":"listed","path":"dia/audio.py","file_url":"https://github.com/nari-labs/dia/blob/HEAD/dia/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd5b74f128417448"}},{"code_sha256_prefix":"230a08e2d42ac7f3","entry":"build_delay_indices","repo":"nari-labs/dia","repo_kind":"listed","path":"dia/audio.py","file_url":"https://github.com/nari-labs/dia/blob/HEAD/dia/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"230a08e2d42ac7f3"}},{"code_sha256_prefix":"176dd1fda856a295","entry":"build_revert_indices","repo":"nari-labs/dia","repo_kind":"listed","path":"dia/audio.py","file_url":"https://github.com/nari-labs/dia/blob/HEAD/dia/audio.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"176dd1fda856a295"}},{"code_sha256_prefix":"591485ad5b203f8f","entry":"create_attn_mask","repo":"nari-labs/dia","repo_kind":"listed","path":"dia/state.py","file_url":"https://github.com/nari-labs/dia/blob/HEAD/dia/state.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"591485ad5b203f8f"}},{"code_sha256_prefix":"746349bd1de0b85d","entry":"custom_scaled_dot_product_attention","repo":"nari-labs/dia","repo_kind":"listed","path":"dia/layers.py","file_url":"https://github.com/nari-labs/dia/blob/HEAD/dia/layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"746349bd1de0b85d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}