{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTAC3FXOUBNT4FHXVT6MSJEDAT","short_pith_number":"pith:YTAC3FXO","schema_version":"1.0","canonical_sha256":"c4c02d96eea05b3e14f7acfcc9248304f984c8b87af89563cc89d2fa4cda3271","source":{"kind":"arxiv","id":"2502.05512","version":1},"attestation_state":"computed","paper":{"title":"IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinchao Wang, Jingchen Shu, Lu Wang, Siyi Zhou, Wei Deng","submitted_at":"2025-02-08T10:23:20Z","abstract_excerpt":"Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities.Here, we introduce the IndexTTS system, which is mainly based on the XTTS and Tortoise model. We add some novel improvements. Specifically, in Chinese scenarios, we adopt a hybrid modeling method that combines characters and pinyin, making the pronunciations of polyphonic characters and long-tail characters controllable. We also performed a comparative analysis of the Vector Quantization (VQ)"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2502.05512","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-02-08T10:23:20Z","cross_cats_sorted":["cs.AI","eess.AS"],"title_canon_sha256":"f7d1d289bfffe9d81627d706c8306d85742d75f6000258e8ee4929edd69e4b26","abstract_canon_sha256":"daf21fe38a8095f07e52349a061950dd19709912a819818cba61371388593a6b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:39.241147Z","signature_b64":"u+r/m6qRhoeOroubpi0fz8uKcWBIJebYnhL0ZmuqWftWILfia8FB9tboXWD7YnyFhdK4nSLvEKHmV7DwgZEFDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4c02d96eea05b3e14f7acfcc9248304f984c8b87af89563cc89d2fa4cda3271","last_reissued_at":"2026-07-05T10:11:39.240697Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:39.240697Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","eess.AS"],"primary_cat":"cs.SD","authors_text":"Jinchao Wang, Jingchen Shu, Lu Wang, Siyi Zhou, Wei Deng","submitted_at":"2025-02-08T10:23:20Z","abstract_excerpt":"Recently, large language model (LLM) based text-to-speech (TTS) systems have gradually become the mainstream in the industry due to their high naturalness and powerful zero-shot voice cloning capabilities.Here, we introduce the IndexTTS system, which is mainly based on the XTTS and Tortoise model. We add some novel improvements. Specifically, in Chinese scenarios, we adopt a hybrid modeling method that combines characters and pinyin, making the pronunciations of polyphonic characters and long-tail characters controllable. We also performed a comparative analysis of the Vector Quantization (VQ)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05512","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2502.05512/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2502.05512","created_at":"2026-07-05T10:11:39.240750+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05512v1","created_at":"2026-07-05T10:11:39.240750+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05512","created_at":"2026-07-05T10:11:39.240750+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTAC3FXOUBNT","created_at":"2026-07-05T10:11:39.240750+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTAC3FXOUBNT4FHX","created_at":"2026-07-05T10:11:39.240750+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTAC3FXO","created_at":"2026-07-05T10:11:39.240750+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.16417","citing_title":"Joycent: Diffusion-based Accent TTS without Accented Phone Prediction","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04680","citing_title":"Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01677","citing_title":"UniVocal: Unified Speech-Singing Code-Switching Synthesis","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31128","citing_title":"UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27258","citing_title":"PilotTTS: A Disciplined Modular Recipe for Competitive Speech Synthesis","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29430","citing_title":"Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic Evaluation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17583","citing_title":"AgentSteerTTS: A Multi-Agent Closed-Loop Framework for Composite-Instruction Text-to-Speech","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16964","citing_title":"SemaVoice: Semantic-Aware Continuous Autoregressive Speech Synthesis","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09318","citing_title":"ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.19414","citing_title":"EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2505.17589","citing_title":"CosyVoice 3: Towards In-the-wild Speech Generation via Scaling-up and Post-training","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08558","citing_title":"WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00688","citing_title":"OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00156","citing_title":"RoboKA: KAN Informed Multimodal Learning for RoboCall Surveillance System","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11103","citing_title":"ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08184","citing_title":"AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09121","citing_title":"Interactive ASR: Towards Human-Like Interaction and Semantic Coherence Evaluation for Agentic Speech Recognition","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16056","citing_title":"AST: Adaptive, Seamless, and Training-Free Precise Speech Editing","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17958","citing_title":"MINT-Bench: A Comprehensive Multilingual Benchmark for Instruction-Following Text-to-Speech","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT","json":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT.json","graph_json":"https://pith.science/api/pith-number/YTAC3FXOUBNT4FHXVT6MSJEDAT/graph.json","events_json":"https://pith.science/api/pith-number/YTAC3FXOUBNT4FHXVT6MSJEDAT/events.json","paper":"https://pith.science/paper/YTAC3FXO"},"agent_actions":{"view_html":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT","download_json":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT.json","view_paper":"https://pith.science/paper/YTAC3FXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05512&json=true","fetch_graph":"https://pith.science/api/pith-number/YTAC3FXOUBNT4FHXVT6MSJEDAT/graph.json","fetch_events":"https://pith.science/api/pith-number/YTAC3FXOUBNT4FHXVT6MSJEDAT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT/action/storage_attestation","attest_author":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT/action/author_attestation","sign_citation":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT/action/citation_signature","submit_replication":"https://pith.science/pith/YTAC3FXOUBNT4FHXVT6MSJEDAT/action/replication_record"}},"created_at":"2026-07-05T10:11:39.240750+00:00","updated_at":"2026-07-05T10:11:39.240750+00:00"}