{"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/voiceflow-efficient-text-to-speech-with","title":"VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching","arxiv_id":"2309.05027","date":"2023-09-10","proceeding":null,"authors":["Yiwei Guo","Chenpeng Du","Ziyang Ma","Xie Chen","Kai Yu"],"abstract":"Although diffusion models in text-to-speech have become a popular choice due to their strong generative ability, the intrinsic complexity of sampling from diffusion models harms their efficiency. Alternatively, we propose VoiceFlow, an acoustic model that utilizes a rectified flow matching algorithm to achieve high synthesis quality with a limited number of sampling steps. VoiceFlow formulates the process of generating mel-spectrograms into an ordinary differential equation conditional on text inputs, whose vector field is then estimated. The rectified flow technique then effectively straightens its sampling trajectory for efficient synthesis. Subjective and objective evaluations on both single and multi-speaker corpora showed the superior synthesis quality of VoiceFlow compared to the diffusion counterpart. Ablation studies further verified the validity of the rectified flow technique in VoiceFlow.","url_abs":"https://arxiv.org/abs/2309.05027v3","url_pdf":"https://arxiv.org/pdf/2309.05027v3.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":"voiceflow-efficient-text-to-speech-with","repo_url":"https://github.com/X-LANCE/VoiceFlow-TTS","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"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":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.05027","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2309.05027"}},"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/X-LANCE/VoiceFlow-TTS","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":1},"by_repo_kind":{"official":{"samples":5,"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":5,"samples":[{"code_sha256_prefix":"483c5361bafc7a07","entry":"batch_beta_binomial_prior_distribution","repo":"X-LANCE/VoiceFlow-TTS","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/X-LANCE/VoiceFlow-TTS/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"483c5361bafc7a07"}},{"code_sha256_prefix":"1d6334c696465ec6","entry":"beta_binomial_prior_distribution","repo":"X-LANCE/VoiceFlow-TTS","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/X-LANCE/VoiceFlow-TTS/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d6334c696465ec6"}},{"code_sha256_prefix":"5bd7a63fb4228d7d","entry":"mle_loss","repo":"X-LANCE/VoiceFlow-TTS","repo_kind":"official","path":"model/utils.py","file_url":"https://github.com/X-LANCE/VoiceFlow-TTS/blob/HEAD/model/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5bd7a63fb4228d7d"}},{"code_sha256_prefix":"a738aab70ae2e603","entry":"wasserstein","repo":"X-LANCE/VoiceFlow-TTS","repo_kind":"official","path":"model/optimal_transport.py","file_url":"https://github.com/X-LANCE/VoiceFlow-TTS/blob/HEAD/model/optimal_transport.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a738aab70ae2e603"}},{"code_sha256_prefix":"c01a3efb274ff778","entry":"intersperse","repo":"X-LANCE/VoiceFlow-TTS","repo_kind":"official","path":"data_loader.py","file_url":"https://github.com/X-LANCE/VoiceFlow-TTS/blob/HEAD/data_loader.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c01a3efb274ff778"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}