{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LH74A367BKTSLINC27WSW2A4RF","short_pith_number":"pith:LH74A367","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"},"canonical_sha256":"59ffc06fdf0aa725a1a2d7ed2b681c896027bfeca0356e371082c38155536534","source":{"kind":"arxiv","id":"2406.04904","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04904","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04904v1","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04904","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"LH74A367BKTS","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"LH74A367BKTSLINC","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"LH74A367","created_at":"2026-07-05T08:28:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LH74A367BKTSLINC27WSW2A4RF","target":"record","payload":{"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"},"canonical_sha256":"59ffc06fdf0aa725a1a2d7ed2b681c896027bfeca0356e371082c38155536534","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"},"source_kind":"arxiv","source_id":"2406.04904","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7Jp3mCsuMjjlT72I/KGuvBfmBiRwP0B/q9Z3c6kJksrDjGDn9MvNbm2rvFmr4OVdxfgf78ahvhTXOpKxaSb0CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T21:46:27.877740Z"},"content_sha256":"4d5eea577210033e08465a633170632c0c63ed3b84f839bea8ab1f476b16243b","schema_version":"1.0","event_id":"sha256:4d5eea577210033e08465a633170632c0c63ed3b84f839bea8ab1f476b16243b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LH74A367BKTSLINC27WSW2A4RF","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mwbcjnv6WP1vzBl7d3vihVfN1rKmxnUe0+YU9sFCltZt+nxmiFVxPKLrA81iuRO9RKHXW97lahOM2YC6P6uaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T21:46:27.878121Z"},"content_sha256":"e4b35acf0158ec7d787fd59b20e75f8a2ba0b56ec162e977eba9b70f1294fa51","schema_version":"1.0","event_id":"sha256:e4b35acf0158ec7d787fd59b20e75f8a2ba0b56ec162e977eba9b70f1294fa51"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/bundle.json","state_url":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LH74A367BKTSLINC27WSW2A4RF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T21:46:27Z","links":{"resolver":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF","bundle":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/bundle.json","state":"https://pith.science/pith/LH74A367BKTSLINC27WSW2A4RF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LH74A367BKTSLINC27WSW2A4RF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LH74A367BKTSLINC27WSW2A4RF","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"17b3cfb405e8e8f835215c4d508bb33cf13dbb64b54ccd9f8af19df86e2f9f3c","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T12:56:11Z","title_canon_sha256":"64d055e85f455141691f6b040bf1c7b141dd93083620c83e6689fb7e4cba8bc7"},"schema_version":"1.0","source":{"id":"2406.04904","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.04904","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"arxiv_version","alias_value":"2406.04904v1","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04904","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"pith_short_12","alias_value":"LH74A367BKTS","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"pith_short_16","alias_value":"LH74A367BKTSLINC","created_at":"2026-07-05T08:28:50Z"},{"alias_kind":"pith_short_8","alias_value":"LH74A367","created_at":"2026-07-05T08:28:50Z"}],"graph_snapshots":[{"event_id":"sha256:e4b35acf0158ec7d787fd59b20e75f8a2ba0b56ec162e977eba9b70f1294fa51","target":"graph","created_at":"2026-07-05T08:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.04904/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T12:56:11Z","title":"XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04904","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4d5eea577210033e08465a633170632c0c63ed3b84f839bea8ab1f476b16243b","target":"record","created_at":"2026-07-05T08:28:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"17b3cfb405e8e8f835215c4d508bb33cf13dbb64b54ccd9f8af19df86e2f9f3c","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-06-07T12:56:11Z","title_canon_sha256":"64d055e85f455141691f6b040bf1c7b141dd93083620c83e6689fb7e4cba8bc7"},"schema_version":"1.0","source":{"id":"2406.04904","kind":"arxiv","version":1}},"canonical_sha256":"59ffc06fdf0aa725a1a2d7ed2b681c896027bfeca0356e371082c38155536534","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"59ffc06fdf0aa725a1a2d7ed2b681c896027bfeca0356e371082c38155536534","first_computed_at":"2026-07-05T08:28:50.703368Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:50.703368Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q5am5UsLbeYhsVNP73Yeq6BXqAjOLyv4nXW1URisbZjRP23unya8HoZeAfYRAXp7GXDA23uO67+kgtLyNhoDDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:50.703872Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.04904","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4d5eea577210033e08465a633170632c0c63ed3b84f839bea8ab1f476b16243b","sha256:e4b35acf0158ec7d787fd59b20e75f8a2ba0b56ec162e977eba9b70f1294fa51"],"state_sha256":"1c42a17bd7fbe2f43dea1cd22add8743b02420205fc5820ebf401f82cd268385"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e0mO5FEg+G9FAGLF6T/hN0D5hWjSVdGi0JbssKqT+UpqGnsiC/YWrZi108zEk86bpK9npavjnl5ElrVC6odBDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T21:46:27.880194Z","bundle_sha256":"c422c99bbe2a56beed283f5ed3c67e393f532ef60f8ce453345597e36139998d"}}