{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FT3HFXQJTCPJDSY24D6BJKBQIM","short_pith_number":"pith:FT3HFXQJ","schema_version":"1.0","canonical_sha256":"2cf672de09989e91cb1ae0fc14a8304301eb53d56e92f69fa63f71c217bff718","source":{"kind":"arxiv","id":"2607.21042","version":1},"attestation_state":"computed","paper":{"title":"Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Junjie Lai, Muyang Du, Shuang Yu","submitted_at":"2026-07-23T08:24:21Z","abstract_excerpt":"Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2 is a state-of-the-art autoregressive TTS model consisting of a GPT, a flow-matching Diffusion Transformer, and a vocoder. Despite its high synthesis quality, its inference speed barely reaches real-time without streaming or batching support. We present Faster IndexTTS-2, which accelerates all neural network components of IndexTTS-2 for production deployment on GPUs using NVIDI"},"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":"2607.21042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T08:24:21Z","cross_cats_sorted":[],"title_canon_sha256":"cae94875c70c772c5ce5864276371361958cb8f545418c53e9b7fb4ee75e908b","abstract_canon_sha256":"eb300311d60ca8e9ba1c16b23302d3b1bde6bdc047f35500366dfd6c2c209bb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:48.778249Z","signature_b64":"nOFkvR++x1E6eDSYnzLH/l445MrmebHZnX/ON+dRKTT4DxCnbT5GKRBfE4Ak5Ohg1mGMFuq6Pz8TVPbLk+tVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cf672de09989e91cb1ae0fc14a8304301eb53d56e92f69fa63f71c217bff718","last_reissued_at":"2026-07-24T01:23:48.777346Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:48.777346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Faster IndexTTS-2: Accelerating and Streaming Autoregressive Zero-Shot Text-to-Speech Synthesis on GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Junjie Lai, Muyang Du, Shuang Yu","submitted_at":"2026-07-23T08:24:21Z","abstract_excerpt":"Autoregressive text-to-speech models achieve strong naturalness but suffer from slow inference due to sequential token generation, limiting their deployment in production applications that require low latency. IndexTTS-2 is a state-of-the-art autoregressive TTS model consisting of a GPT, a flow-matching Diffusion Transformer, and a vocoder. Despite its high synthesis quality, its inference speed barely reaches real-time without streaming or batching support. We present Faster IndexTTS-2, which accelerates all neural network components of IndexTTS-2 for production deployment on GPUs using NVIDI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21042","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/2607.21042/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":"2607.21042","created_at":"2026-07-24T01:23:48.777784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.21042v1","created_at":"2026-07-24T01:23:48.777784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21042","created_at":"2026-07-24T01:23:48.777784+00:00"},{"alias_kind":"pith_short_12","alias_value":"FT3HFXQJTCPJ","created_at":"2026-07-24T01:23:48.777784+00:00"},{"alias_kind":"pith_short_16","alias_value":"FT3HFXQJTCPJDSY2","created_at":"2026-07-24T01:23:48.777784+00:00"},{"alias_kind":"pith_short_8","alias_value":"FT3HFXQJ","created_at":"2026-07-24T01:23:48.777784+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/FT3HFXQJTCPJDSY24D6BJKBQIM","json":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM.json","graph_json":"https://pith.science/api/pith-number/FT3HFXQJTCPJDSY24D6BJKBQIM/graph.json","events_json":"https://pith.science/api/pith-number/FT3HFXQJTCPJDSY24D6BJKBQIM/events.json","paper":"https://pith.science/paper/FT3HFXQJ"},"agent_actions":{"view_html":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM","download_json":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM.json","view_paper":"https://pith.science/paper/FT3HFXQJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.21042&json=true","fetch_graph":"https://pith.science/api/pith-number/FT3HFXQJTCPJDSY24D6BJKBQIM/graph.json","fetch_events":"https://pith.science/api/pith-number/FT3HFXQJTCPJDSY24D6BJKBQIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM/action/storage_attestation","attest_author":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM/action/author_attestation","sign_citation":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM/action/citation_signature","submit_replication":"https://pith.science/pith/FT3HFXQJTCPJDSY24D6BJKBQIM/action/replication_record"}},"created_at":"2026-07-24T01:23:48.777784+00:00","updated_at":"2026-07-24T01:23:48.777784+00:00"}