{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LH74A367BKTSLINC27WSW2A4RF","short_pith_number":"pith:LH74A367","schema_version":"1.0","canonical_sha256":"59ffc06fdf0aa725a1a2d7ed2b681c896027bfeca0356e371082c38155536534","source":{"kind":"arxiv","id":"2406.04904","version":1},"attestation_state":"computed","paper":{"title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aya Aljafari, Edresson Casanova, Eren G\\\"olge, G\\\"orkem G\\\"oknar, Iulian Gulea, Joshua Meyer, Julian Weber, Kelly Davis, Logan Hart, Reuben Morais, Samuel Olayemi","submitted_at":"2024-06-07T12:56:11Z","abstract_excerpt":"Most Zero-shot Multi-speaker TTS (ZS-TTS) systems support only a single language. Although models like YourTTS, VALL-E X, Mega-TTS 2, and Voicebox explored Multilingual ZS-TTS they are limited to just a few high/medium resource languages, limiting the applications of these models in most of the low/medium resource languages. In this paper, we aim to alleviate this issue by proposing and making publicly available the XTTS system. Our method builds upon the Tortoise model and adds several novel modifications to enable multilingual training, improve voice cloning, and enable faster training and i"},"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":"2406.04904","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T12:56:11Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"64d055e85f455141691f6b040bf1c7b141dd93083620c83e6689fb7e4cba8bc7","abstract_canon_sha256":"17b3cfb405e8e8f835215c4d508bb33cf13dbb64b54ccd9f8af19df86e2f9f3c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:50.703872Z","signature_b64":"Q5am5UsLbeYhsVNP73Yeq6BXqAjOLyv4nXW1URisbZjRP23unya8HoZeAfYRAXp7GXDA23uO67+kgtLyNhoDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59ffc06fdf0aa725a1a2d7ed2b681c896027bfeca0356e371082c38155536534","last_reissued_at":"2026-07-05T08:28:50.703368Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:50.703368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Aya Aljafari, Edresson Casanova, Eren G\\\"olge, G\\\"orkem G\\\"oknar, Iulian Gulea, Joshua Meyer, Julian Weber, Kelly Davis, Logan Hart, Reuben Morais, Samuel Olayemi","submitted_at":"2024-06-07T12:56:11Z","abstract_excerpt":"Most Zero-shot Multi-speaker TTS (ZS-TTS) systems support only a single language. Although models like YourTTS, VALL-E X, Mega-TTS 2, and Voicebox explored Multilingual ZS-TTS they are limited to just a few high/medium resource languages, limiting the applications of these models in most of the low/medium resource languages. In this paper, we aim to alleviate this issue by proposing and making publicly available the XTTS system. Our method builds upon the Tortoise model and adds several novel modifications to enable multilingual training, improve voice cloning, and enable faster training and i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04904","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/2406.04904/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":"2406.04904","created_at":"2026-07-05T08:28:50.703424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04904v1","created_at":"2026-07-05T08:28:50.703424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04904","created_at":"2026-07-05T08:28:50.703424+00:00"},{"alias_kind":"pith_short_12","alias_value":"LH74A367BKTS","created_at":"2026-07-05T08:28:50.703424+00:00"},{"alias_kind":"pith_short_16","alias_value":"LH74A367BKTSLINC","created_at":"2026-07-05T08:28:50.703424+00:00"},{"alias_kind":"pith_short_8","alias_value":"LH74A367","created_at":"2026-07-05T08:28:50.703424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06054","citing_title":"BlueMagpie-TTS: A Token-Efficient Tokenizer, Language Model, and TTS for Taiwanese-Accent Code-Switching Speech","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26618","citing_title":"Closing the Quality Gap in Low-Resource Text-to-Speech: LoRA Fine-Tuning of VoxCPM2 for Khmer and Korean","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21343","citing_title":"An Evaluation Framework for Text-to-Speech Voice Reconstruction","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18319","citing_title":"ASTRA: A Scalable Next-Generation ATCO Training Simulator with Autonomous Simpilots","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09141","citing_title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06928","citing_title":"VoxCPM2 Technical Report","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28002","citing_title":"Dialogue to Detection: A Multimodal Hybrid NLP Pipeline for Insurance Fraud Detection","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31247","citing_title":"FlexiSLM: A Dynamic and Controllable Frame Rate Spoken Language Model","ref_index":173,"is_internal_anchor":false},{"citing_arxiv_id":"2510.19414","citing_title":"EchoFake: A Replay-Aware Dataset for Practical Speech Deepfake Detection","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05611","citing_title":"X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05611","citing_title":"X-Voice: Enabling Everyone to Speak 30 Languages via Zero-Shot Cross-Lingual Voice Cloning","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11283","citing_title":"Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented Survey","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09111","citing_title":"PS-TTS: Phonetic Synchronization in Text-to-Speech for Achieving Natural Automated Dubbing","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13229","citing_title":"ProSDD: Learning Prosodic Representations for Speech Deepfake Detection against Expressive and Emotional Attacks","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF","json":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF.json","graph_json":"https://pith.science/api/pith-number/LH74A367BKTSLINC27WSW2A4RF/graph.json","events_json":"https://pith.science/api/pith-number/LH74A367BKTSLINC27WSW2A4RF/events.json","paper":"https://pith.science/paper/LH74A367"},"agent_actions":{"view_html":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF","download_json":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF.json","view_paper":"https://pith.science/paper/LH74A367","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04904&json=true","fetch_graph":"https://pith.science/api/pith-number/LH74A367BKTSLINC27WSW2A4RF/graph.json","fetch_events":"https://pith.science/api/pith-number/LH74A367BKTSLINC27WSW2A4RF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/action/storage_attestation","attest_author":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/action/author_attestation","sign_citation":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/action/citation_signature","submit_replication":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/action/replication_record"}},"created_at":"2026-07-05T08:28:50.703424+00:00","updated_at":"2026-07-05T08:28:50.703424+00:00"}