{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M4EMYDIESKGPIQ6VO2GSOQAMXU","short_pith_number":"pith:M4EMYDIE","schema_version":"1.0","canonical_sha256":"6708cc0d04928cf443d5768d27400cbd0607128d83e525e7e40b9b91f50bb03c","source":{"kind":"arxiv","id":"2606.09141","version":1},"attestation_state":"computed","paper":{"title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dake Guo, Guobin Ma, Hanke Xie, Huakang Chen, Jingbin Hu, Kejie Xu, Lei Xi, Rui Huang, Ruonan You, Weiguo Tan, Wenhao Li, Xiaming Ren, Xianrong Wang","submitted_at":"2026-06-08T07:39:26Z","abstract_excerpt":"Recent progress in speech dialogue systems requires Text-to-Speech (TTS) models to be faster and more responsive. Modern speech dialogue systems impose two primary requirements on TTS models: low latency and support for streaming inputs and outputs. However, most existing single-codebook LLM-based TTS methods rely on multi-stage pipelines that lack native streaming capabilities. These systems typically suffer from high end-to-end latency due to slow autoregressive prediction and multi-step flow matching. To address these limitations, we propose FlashTTS, an open-source and low-latency streamin"},"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":"2606.09141","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-08T07:39:26Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"99c3d6d37d0d35e093fd7b71cb55627953bb184277b2f1ba639fb507c230c0cb","abstract_canon_sha256":"675b9357576bfa70ae99ca4245a3dfcd6334973e91110b14963d306179794f3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:02.234037Z","signature_b64":"Xnk/IyBSQi8ywBVl/5dbkD45IVK8khpnFtuM5O2lGYPAfoaRDU31Igb1Czb2scQ6LKGQLI/3cPt17Wio/V8eAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6708cc0d04928cf443d5768d27400cbd0607128d83e525e7e40b9b91f50bb03c","last_reissued_at":"2026-06-09T02:08:02.233183Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:02.233183Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FlashTTS: Fast Streaming TTS with MTP Acceleration and X-pred Mean Flow Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Dake Guo, Guobin Ma, Hanke Xie, Huakang Chen, Jingbin Hu, Kejie Xu, Lei Xi, Rui Huang, Ruonan You, Weiguo Tan, Wenhao Li, Xiaming Ren, Xianrong Wang","submitted_at":"2026-06-08T07:39:26Z","abstract_excerpt":"Recent progress in speech dialogue systems requires Text-to-Speech (TTS) models to be faster and more responsive. Modern speech dialogue systems impose two primary requirements on TTS models: low latency and support for streaming inputs and outputs. However, most existing single-codebook LLM-based TTS methods rely on multi-stage pipelines that lack native streaming capabilities. These systems typically suffer from high end-to-end latency due to slow autoregressive prediction and multi-step flow matching. To address these limitations, we propose FlashTTS, an open-source and low-latency streamin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09141","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/2606.09141/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":"2606.09141","created_at":"2026-06-09T02:08:02.233337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09141v1","created_at":"2026-06-09T02:08:02.233337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09141","created_at":"2026-06-09T02:08:02.233337+00:00"},{"alias_kind":"pith_short_12","alias_value":"M4EMYDIESKGP","created_at":"2026-06-09T02:08:02.233337+00:00"},{"alias_kind":"pith_short_16","alias_value":"M4EMYDIESKGPIQ6V","created_at":"2026-06-09T02:08:02.233337+00:00"},{"alias_kind":"pith_short_8","alias_value":"M4EMYDIE","created_at":"2026-06-09T02:08:02.233337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU","json":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU.json","graph_json":"https://pith.science/api/pith-number/M4EMYDIESKGPIQ6VO2GSOQAMXU/graph.json","events_json":"https://pith.science/api/pith-number/M4EMYDIESKGPIQ6VO2GSOQAMXU/events.json","paper":"https://pith.science/paper/M4EMYDIE"},"agent_actions":{"view_html":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU","download_json":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU.json","view_paper":"https://pith.science/paper/M4EMYDIE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09141&json=true","fetch_graph":"https://pith.science/api/pith-number/M4EMYDIESKGPIQ6VO2GSOQAMXU/graph.json","fetch_events":"https://pith.science/api/pith-number/M4EMYDIESKGPIQ6VO2GSOQAMXU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU/action/storage_attestation","attest_author":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU/action/author_attestation","sign_citation":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU/action/citation_signature","submit_replication":"https://pith.science/pith/M4EMYDIESKGPIQ6VO2GSOQAMXU/action/replication_record"}},"created_at":"2026-06-09T02:08:02.233337+00:00","updated_at":"2026-06-09T02:08:02.233337+00:00"}