{"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/2503-01710","title":"Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens","arxiv_id":"2503.01710","date":"2025-03-03","proceeding":null,"authors":["Xinsheng Wang","Mingqi Jiang","Ziyang Ma","Ziyu Zhang","Songxiang Liu","Linqin Li","Zheng Liang","Qixi Zheng","Rui Wang","Xiaoqin Feng","Weizhen Bian","Zhen Ye","Sitong Cheng","Ruibin Yuan","Zhixian Zhao","Xinfa Zhu","Jiahao Pan","Liumeng Xue","Pengcheng Zhu","Yunlin Chen","Zhifei Li","Xie Chen","Lei Xie","Yike Guo","Wei Xue"],"abstract":"Recent advancements in large language models (LLMs) have driven significant progress in zero-shot text-to-speech (TTS) synthesis. However, existing foundation models rely on multi-stage processing or complex architectures for predicting multiple codebooks, limiting efficiency and integration flexibility. To overcome these challenges, we introduce Spark-TTS, a novel system powered by BiCodec, a single-stream speech codec that decomposes speech into two complementary token types: low-bitrate semantic tokens for linguistic content and fixed-length global tokens for speaker attributes. This disentangled representation, combined with the Qwen2.5 LLM and a chain-of-thought (CoT) generation approach, enables both coarse-grained control (e.g., gender, speaking style) and fine-grained adjustments (e.g., precise pitch values, speaking rate). To facilitate research in controllable TTS, we introduce VoxBox, a meticulously curated 100,000-hour dataset with comprehensive attribute annotations. Extensive experiments demonstrate that Spark-TTS not only achieves state-of-the-art zero-shot voice cloning but also generates highly customizable voices that surpass the limitations of reference-based synthesis. Source code, pre-trained models, and audio samples are available at https://github.com/SparkAudio/Spark-TTS.","url_abs":"https://arxiv.org/abs/2503.01710v1","url_pdf":"https://arxiv.org/pdf/2503.01710v1.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":"2503-01710","repo_url":"https://github.com/sparkaudio/spark-tts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"attribute","task_name":"Attribute"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"voice-cloning","task_name":"Voice Cloning"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2503.01710","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.01710"}},"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/sparkaudio/spark-tts","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":2,"ran":1,"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":"f247e4748f379a76","entry":"snake","repo":"sparkaudio/spark-tts","repo_kind":"official","path":"sparktts/modules/blocks/layers.py","file_url":"https://github.com/sparkaudio/spark-tts/blob/HEAD/sparktts/modules/blocks/layers.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f247e4748f379a76"}},{"code_sha256_prefix":"fbe2582b48c9abce","entry":"prepare_request","repo":"sparkaudio/spark-tts","repo_kind":"official","path":"runtime/triton_trtllm/client_http.py","file_url":"https://github.com/sparkaudio/spark-tts/blob/HEAD/runtime/triton_trtllm/client_http.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":"fbe2582b48c9abce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}