{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TZGHQ5OQVZ5VEFTHW5YUCEH7AK","short_pith_number":"pith:TZGHQ5OQ","schema_version":"1.0","canonical_sha256":"9e4c7875d0ae7b521667b7714110ff02907eccc83fd3f08af60c42d5ec895610","source":{"kind":"arxiv","id":"2606.24320","version":1},"attestation_state":"computed","paper":{"title":"ZONOS2 Technical Report","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Beren Millidge, Gabriel Clark, George Close, Mohamed Osman, Sofian Mejjoute","submitted_at":"2026-06-23T08:57:34Z","abstract_excerpt":"We present ZONOS2 8B, our latest TTS model, which achieves state-of-the-art naturalness, prosody, and voice cloning fidelity. We improve upon Zonos-v0.1 across scale, data, and training recipe. We scale the model from 1.6B to 8B total parameters (900M active) with a novel mixture-of-experts (MoE) backbone, improving inference latency and throughput. We expand our training corpus from 200K to over 6M hours using a new data processing pipeline, and we simplify our post-training and conditioning recipes to improve naturalness and voice cloning fidelity. We evaluate ZONOS2 8B on quality, speaker s"},"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":"2606.24320","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-06-23T08:57:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cc7a8dd827350e846ca0ced7ed4af482a77b10f7a5d146bda71a5ba60e71156b","abstract_canon_sha256":"e8ae289d48c50289d0f5f0267693d22626bdce651def247c04e7a24d825614c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:14:49.912066Z","signature_b64":"kyA3cVJL0oc5UaMWRetKczi25BbU+VTNpFZ4nhkqV/KTpI2EiIDRwmpr11TX9pJMiVaSqck9chKx6BKxSoTsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e4c7875d0ae7b521667b7714110ff02907eccc83fd3f08af60c42d5ec895610","last_reissued_at":"2026-06-24T01:14:49.911587Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:14:49.911587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ZONOS2 Technical Report","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Beren Millidge, Gabriel Clark, George Close, Mohamed Osman, Sofian Mejjoute","submitted_at":"2026-06-23T08:57:34Z","abstract_excerpt":"We present ZONOS2 8B, our latest TTS model, which achieves state-of-the-art naturalness, prosody, and voice cloning fidelity. We improve upon Zonos-v0.1 across scale, data, and training recipe. We scale the model from 1.6B to 8B total parameters (900M active) with a novel mixture-of-experts (MoE) backbone, improving inference latency and throughput. We expand our training corpus from 200K to over 6M hours using a new data processing pipeline, and we simplify our post-training and conditioning recipes to improve naturalness and voice cloning fidelity. We evaluate ZONOS2 8B on quality, speaker s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24320","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/2606.24320/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":"2606.24320","created_at":"2026-06-24T01:14:49.911639+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.24320v1","created_at":"2026-06-24T01:14:49.911639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24320","created_at":"2026-06-24T01:14:49.911639+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZGHQ5OQVZ5V","created_at":"2026-06-24T01:14:49.911639+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZGHQ5OQVZ5VEFTH","created_at":"2026-06-24T01:14:49.911639+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZGHQ5OQ","created_at":"2026-06-24T01:14:49.911639+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/TZGHQ5OQVZ5VEFTHW5YUCEH7AK","json":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK.json","graph_json":"https://pith.science/api/pith-number/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/graph.json","events_json":"https://pith.science/api/pith-number/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/events.json","paper":"https://pith.science/paper/TZGHQ5OQ"},"agent_actions":{"view_html":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK","download_json":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK.json","view_paper":"https://pith.science/paper/TZGHQ5OQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.24320&json=true","fetch_graph":"https://pith.science/api/pith-number/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/graph.json","fetch_events":"https://pith.science/api/pith-number/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/action/storage_attestation","attest_author":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/action/author_attestation","sign_citation":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/action/citation_signature","submit_replication":"https://pith.science/pith/TZGHQ5OQVZ5VEFTHW5YUCEH7AK/action/replication_record"}},"created_at":"2026-06-24T01:14:49.911639+00:00","updated_at":"2026-06-24T01:14:49.911639+00:00"}