{"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/neural-codec-language-models-are-zero-shot","title":"Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers","arxiv_id":"2301.02111","date":"2023-01-05","proceeding":null,"authors":["Chengyi Wang","Sanyuan Chen","Yu Wu","Ziqiang Zhang","Long Zhou","Shujie Liu","Zhuo Chen","Yanqing Liu","Huaming Wang","Jinyu Li","Lei He","Sheng Zhao","Furu Wei"],"abstract":"We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find Vall-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. See https://aka.ms/valle for demos of our work.","url_abs":"https://arxiv.org/abs/2301.02111v1","url_pdf":"https://arxiv.org/pdf/2301.02111v1.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":"neural-codec-language-models-are-zero-shot","repo_url":"https://github.com/microsoft/unilm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-codec-language-models-are-zero-shot","repo_url":"https://github.com/2noise/chattts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"paper_slug":"neural-codec-language-models-are-zero-shot","repo_url":"https://github.com/lifeiteng/vall-e","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"neural-codec-language-models-are-zero-shot","repo_url":"https://github.com/plachtaa/vall-e-x","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-codec-language-models-are-zero-shot","repo_url":"https://github.com/serp-ai/bark-with-voice-clone","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"neural-codec-language-models-are-zero-shot","repo_url":"https://github.com/suno-ai/bark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"neural-codec-language-models-are-zero-shot","repo_url":"https://github.com/enhuiz/vall-e","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"text-to-speech-synthesis","task_name":"Text-To-Speech Synthesis"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[{"method_slug":null,"method_name":"(USA Guide)"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"lamb","method_name":"LAMB"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.02111","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.02111"}},"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/serp-ai/bark-with-voice-clone","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/suno-ai/bark","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lifeiteng/vall-e","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/2noise/chattts","reach":{"status":"ok","spdx":"AGPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/plachtaa/vall-e-x","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/microsoft/unilm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/enhuiz/vall-e","reach":null}],"summary":{"ran":6},"by_repo_kind":{"listed":{"samples":6,"ran":6,"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":"ffec7b2aa35d0253","entry":"calc_lr","repo":"lifeiteng/vall-e","repo_kind":"listed","path":"valle/modules/scheduler.py","file_url":"https://github.com/lifeiteng/vall-e/blob/HEAD/valle/modules/scheduler.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ffec7b2aa35d0253"}},{"code_sha256_prefix":"982b9083b5a41368","entry":"random_cast_to_half","repo":"lifeiteng/vall-e","repo_kind":"listed","path":"valle/modules/scaling.py","file_url":"https://github.com/lifeiteng/vall-e/blob/HEAD/valle/modules/scaling.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"982b9083b5a41368"}},{"code_sha256_prefix":"1d72f492e19080e6","entry":"random_clamp","repo":"lifeiteng/vall-e","repo_kind":"listed","path":"valle/modules/scaling.py","file_url":"https://github.com/lifeiteng/vall-e/blob/HEAD/valle/modules/scaling.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1d72f492e19080e6"}},{"code_sha256_prefix":"c124aa8bd6b9ebe9","entry":"softmax","repo":"lifeiteng/vall-e","repo_kind":"listed","path":"valle/modules/scaling.py","file_url":"https://github.com/lifeiteng/vall-e/blob/HEAD/valle/modules/scaling.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c124aa8bd6b9ebe9"}},{"code_sha256_prefix":"99a311d99448f881","entry":"top_k_top_p_filtering","repo":"lifeiteng/vall-e","repo_kind":"listed","path":"valle/models/valle.py","file_url":"https://github.com/lifeiteng/vall-e/blob/HEAD/valle/models/valle.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"99a311d99448f881"}},{"code_sha256_prefix":"fb8e21d446dcf26f","entry":"topk_sampling","repo":"lifeiteng/vall-e","repo_kind":"listed","path":"valle/models/valle.py","file_url":"https://github.com/lifeiteng/vall-e/blob/HEAD/valle/models/valle.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fb8e21d446dcf26f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}