{"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/comospeech-one-step-speech-and-singing-voice","title":"CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model","arxiv_id":"2305.06908","date":"2023-05-11","proceeding":null,"authors":["Zhen Ye","Wei Xue","Xu Tan","Jie Chen","Qifeng Liu","Yike Guo"],"abstract":"Denoising diffusion probabilistic models (DDPMs) have shown promising performance for speech synthesis. However, a large number of iterative steps are required to achieve high sample quality, which restricts the inference speed. Maintaining sample quality while increasing sampling speed has become a challenging task. In this paper, we propose a \"Co\"nsistency \"Mo\"del-based \"Speech\" synthesis method, CoMoSpeech, which achieve speech synthesis through a single diffusion sampling step while achieving high audio quality. The consistency constraint is applied to distill a consistency model from a well-designed diffusion-based teacher model, which ultimately yields superior performances in the distilled CoMoSpeech. Our experiments show that by generating audio recordings by a single sampling step, the CoMoSpeech achieves an inference speed more than 150 times faster than real-time on a single NVIDIA A100 GPU, which is comparable to FastSpeech2, making diffusion-sampling based speech synthesis truly practical. Meanwhile, objective and subjective evaluations on text-to-speech and singing voice synthesis show that the proposed teacher models yield the best audio quality, and the one-step sampling based CoMoSpeech achieves the best inference speed with better or comparable audio quality to other conventional multi-step diffusion model baselines. Audio samples are available at https://comospeech.github.io/.","url_abs":"https://arxiv.org/abs/2305.06908v4","url_pdf":"https://arxiv.org/pdf/2305.06908v4.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":"comospeech-one-step-speech-and-singing-voice","repo_url":"https://github.com/zhenye234/CoMoSpeech","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"singing-voice-synthesis","task_name":"Singing Voice Synthesis"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.06908","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.06908"}},"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/zhenye234/CoMoSpeech","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":3,"unverified":5},"by_repo_kind":{"official":{"samples":9,"ran":4,"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":"59ae0708b1e8d94b","entry":"convert_pad_shape","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/model/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59ae0708b1e8d94b"}},{"code_sha256_prefix":"7137577cbef51217","entry":"discriminator_loss","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"hifi-gan/models.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/hifi-gan/models.py","link_basis":"plan_row","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":"7137577cbef51217"}},{"code_sha256_prefix":"e453b51f0ed5fb28","entry":"feature_loss","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"hifi-gan/models.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/hifi-gan/models.py","link_basis":"plan_row","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":"e453b51f0ed5fb28"}},{"code_sha256_prefix":"1a9d74439d969cfd","entry":"generator_loss","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"hifi-gan/models.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/hifi-gan/models.py","link_basis":"plan_row","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":"1a9d74439d969cfd"}},{"code_sha256_prefix":"a655832746b54bdc","entry":"fix_len_compatibility","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/model/utils.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":"a655832746b54bdc"}},{"code_sha256_prefix":"c01a3efb274ff778","entry":"intersperse","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/utils.py","link_basis":"harvester_set","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":"c01a3efb274ff778"}},{"code_sha256_prefix":"65dde9c5f8924434","entry":"latest_checkpoint_path","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/utils.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":"65dde9c5f8924434"}},{"code_sha256_prefix":"630bab9e2a9566ca","entry":"parse_filelist","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"utils.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/utils.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":"630bab9e2a9566ca"}},{"code_sha256_prefix":"71ed8b8d6ed2bf01","entry":"sequence_mask","repo":"zhenye234/CoMoSpeech","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/zhenye234/CoMoSpeech/blob/HEAD/model/utils.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":"71ed8b8d6ed2bf01"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}