{"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/styletts-2-towards-human-level-text-to-speech","title":"StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models","arxiv_id":"2306.07691","date":"2023-06-13","proceeding":"NeurIPS 2023 11","authors":["Yinghao Aaron Li","Cong Han","Vinay S. Raghavan","Gavin Mischler","Nima Mesgarani"],"abstract":"In this paper, we present StyleTTS 2, a text-to-speech (TTS) model that leverages style diffusion and adversarial training with large speech language models (SLMs) to achieve human-level TTS synthesis. StyleTTS 2 differs from its predecessor by modeling styles as a latent random variable through diffusion models to generate the most suitable style for the text without requiring reference speech, achieving efficient latent diffusion while benefiting from the diverse speech synthesis offered by diffusion models. Furthermore, we employ large pre-trained SLMs, such as WavLM, as discriminators with our novel differentiable duration modeling for end-to-end training, resulting in improved speech naturalness. StyleTTS 2 surpasses human recordings on the single-speaker LJSpeech dataset and matches it on the multispeaker VCTK dataset as judged by native English speakers. Moreover, when trained on the LibriTTS dataset, our model outperforms previous publicly available models for zero-shot speaker adaptation. This work achieves the first human-level TTS on both single and multispeaker datasets, showcasing the potential of style diffusion and adversarial training with large SLMs. The audio demos and source code are available at https://styletts2.github.io/.","url_abs":"https://arxiv.org/abs/2306.07691v2","url_pdf":"https://arxiv.org/pdf/2306.07691v2.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":"styletts-2-towards-human-level-text-to-speech","repo_url":"https://github.com/yl4579/StyleTTS2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-to-speech-on","task":"Text to Speech","dataset":".","model":"mio","rank_in_archive_order":1,"of":1,"metrics":{"0-shot MRR":"mio"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2306.07691","atlas_url":"https://app.syntology.ai/?focus=2306.07691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.07691"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/yl4579/StyleTTS2","reach":null}],"summary":{"unverified":4},"by_repo_kind":{"listed":{"samples":4,"ran":0,"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":"6b5cd35dc42d61ba","entry":"AudioDiffusionConditional","repo":"yl4579/StyleTTS2","repo_kind":"listed","path":"Modules/diffusion/diffusion.py","file_url":"https://github.com/yl4579/StyleTTS2/blob/HEAD/Modules/diffusion/diffusion.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":"6b5cd35dc42d61ba"}},{"code_sha256_prefix":"1ad83a971a9e505a","entry":"Model1d","repo":"yl4579/StyleTTS2","repo_kind":"listed","path":"Modules/diffusion/diffusion.py","file_url":"https://github.com/yl4579/StyleTTS2/blob/HEAD/Modules/diffusion/diffusion.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":"1ad83a971a9e505a"}},{"code_sha256_prefix":"c759f695be238679","entry":"get_default_model_kwargs","repo":"yl4579/StyleTTS2","repo_kind":"listed","path":"Modules/diffusion/diffusion.py","file_url":"https://github.com/yl4579/StyleTTS2/blob/HEAD/Modules/diffusion/diffusion.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":"c759f695be238679"}},{"code_sha256_prefix":"2f586a9469950a08","entry":"get_default_sampling_kwargs","repo":"yl4579/StyleTTS2","repo_kind":"listed","path":"Modules/diffusion/diffusion.py","file_url":"https://github.com/yl4579/StyleTTS2/blob/HEAD/Modules/diffusion/diffusion.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":"2f586a9469950a08"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}