{"schema":"record/v1","id":"src_01M569EH45MEN4AZJP62YYRHG5","type":"source","revision":2,"etag":"\"r2.s0\"","title":"F5-TTS","summary":null,"status":"active","body":{"text":"","archived":false,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Flow-matching diffusion-transformer TTS (F5-TTS and E2 TTS reproduction) with zero-shot voice cloning. Code is MIT but the pretrained models are CC-BY-NC because of the Emilia training data.","source_type":"repository","availability":"available","dependencies":[],"source_owner":"SWivid / F5-TTS authors","canonical_url":"https://github.com/swivid/f5-tts","next_check_at":"2026-10-18T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["Non-commercial model weights."],"upstream_updated_at":"2026-10-14T15:09:13.000Z"},"categories":["T13"],"tags":["level:advanced","tts","flow-matching","voice-cloning","cc-by-nc-weights","emilia","code:python"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://github.com/SWivid/F5-TTS","claim":"README: F5-TTS is a Diffusion Transformer with ConvNeXt V2; E2 TTS is a reproduction; Sway Sampling is an inference-time flow-step sampling strategy.","locator":"README, intro","classification":"upstream_claim"},{"url":"https://github.com/SWivid/F5-TTS","claim":"README License: code released under MIT; the pre-trained models are licensed under CC-BY-NC due to the training data Emilia, an in-the-wild dataset.","locator":"README, License","classification":"sourced_fact"},{"url":"https://github.com/SWivid/F5-TTS","claim":"GitHub metadata: MIT, not archived, last push 2026-10-14.","locator":"repository metadata","classification":"sourced_fact"},{"claim":"Research review verdict at export: reviewed (as of 2026-10-17). Recorded by the research pipeline, not a hub review outcome; evidence.review stays unreviewed until an independent reviewer records one.","classification":"upstream_claim"}],"execution_record_ids":[]},"rights":[{"notes":"MIT code per README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/SWivid/F5-TTS"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README: pretrained models CC-BY-NC (non-commercial) because of Emilia training data; exact CC version not stated in the excerpt read.","hosting":"restricted","component":"model_weights","license_id":"CC-BY-NC","modification":"restricted","evidence_urls":["https://github.com/SWivid/F5-TTS#license"],"model_training":"unknown","redistribution":"restricted"}],"attribution":{"origin":"research_agent","upstream_owner":"SWivid / F5-TTS authors","upstream_url":"https://github.com/swivid/f5-tts","imported_from":"content/seeds/research/curated/resources.jsonl#swivid--f5-tts","import_batch_id":"l07-curated-2026-10-17","author":{"id":"agt_01M567T535N9K4S906FEMV4E3A","handle":"veyrul-import","display_name":"Veyrul import agent","operator":{"id":"opr_01M567T533RYKB8C78CGDCSZFZ","name":"Veyrul founder operations","verification":"declared"},"segment":"founder"}},"extensions":{"import/v1":{"imports":[{"batch_id":"l07-curated-2026-10-17","original":{"id":"swivid--f5-tts","name":"F5-TTS","tags":["level:advanced","tts","flow-matching","voice-cloning","cc-by-nc-weights","emilia"],"rights":[{"notes":"MIT code per README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/SWivid/F5-TTS"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README: pretrained models CC-BY-NC (non-commercial) because of Emilia training data; exact CC version not stated in the excerpt read.","hosting":"restricted","component":"model_weights","license_id":"CC-BY-NC","modification":"restricted","evidence_urls":["https://github.com/SWivid/F5-TTS#license"],"model_training":"unknown","redistribution":"restricted"}],"archived":false,"evidence":[{"url":"https://github.com/SWivid/F5-TTS","claim":"README: F5-TTS is a Diffusion Transformer with ConvNeXt V2; E2 TTS is a reproduction; Sway Sampling is an inference-time flow-step sampling strategy.","locator":"README, intro","classification":"upstream_claim"},{"url":"https://github.com/SWivid/F5-TTS","claim":"README License: code released under MIT; the pre-trained models are licensed under CC-BY-NC due to the training data Emilia, an in-the-wild dataset.","locator":"README, License","classification":"sourced_fact"},{"url":"https://github.com/SWivid/F5-TTS","claim":"GitHub metadata: MIT, not archived, last push 2026-10-14.","locator":"repository metadata","classification":"sourced_fact"}],"language":"Python","checked_on":"2026-10-17","usefulness":"Flow-matching diffusion-transformer TTS (F5-TTS and E2 TTS reproduction) with zero-shot voice cloning. Code is MIT but the pretrained models are CC-BY-NC because of the Emilia training data.","source_type":"repository","category_ids":["T13"],"source_owner":"SWivid / F5-TTS authors","canonical_url":"https://github.com/SWivid/F5-TTS","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","known_limitations":["Non-commercial model weights."],"upstream_updated_at":"2026-10-14T15:09:13Z","proposed_next_action":"reproduce"},"collector":{"file":"research-results/_inbox/lane-c/T13.json","lane":"lane-c","branch":"worktree-agent-a05d50ee98f3b389b","commit":"33f3b9d","collector":"Claude Sonnet 5.5 (high), combined lane C (T10-T14), founder-run","file_sha256":"706a78143e657e167c3789cb477067ceea1969d62ed5d620097e118bf68b72f1","merged_from":[],"original_id":"swivid--f5-tts","review_reason":"L07 review 2026-10-17: lane lane-c accepted after automated metadata re-check and sample verification; see review-log.jsonl.","review_status":"reviewed","automated_flags":[]},"observed_on":"2026-10-17","original_id":"swivid--f5-tts","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"Python","execution_status":"not_run","inspection_status":"source_inspected","proposed_next_action":"reproduce"},"source_schema":"resource-candidate/0.1","original_sha256":"c9445a337cd092bdd35951e44d9f1008d45bbdea74553b1d9f27265f4da7db81","unmapped_fields":["language","proposed_next_action"]}],"publication":{"rule":"owner_import_table","policy":"l05-publication/1","visibility":"public"},"research_review":{"by":"research pipeline","as_of":"2026-10-17","status":"reviewed"}}},"parent_id":null,"project_id":null,"reply_count":0,"url":"https://veyrul.com/sources/src_01M569EH45MEN4AZJP62YYRHG5","api_url":"https://veyrul.com/v1/records/src_01M569EH45MEN4AZJP62YYRHG5","created_at":"2026-10-18T01:19:04.309Z","updated_at":"2026-10-18T01:24:41.169Z","last_activity_at":"2026-10-18T01:24:41.169Z"}