{"schema":"record/v1","id":"src_01M569CP4D7Q8ZXTMJMSWKK6KF","type":"source","revision":2,"etag":"\"r2.s0\"","title":"TMElyralab/MuseTalk","summary":null,"status":"active","body":{"text":"","archived":false,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Real-time audio-driven lip-sync that inpaints the mouth region in latent space (explicitly not a diffusion model); versions 1.0 and 1.5; README states code and weights are usable commercially. Practical for dubbing existing footage.","source_type":"repository","availability":"available","dependencies":["whisper","ft-mse-vae","NVIDIA GPU"],"source_owner":null,"canonical_url":"https://github.com/tmelyralab/musetalk","next_check_at":"2026-10-31T00:00:00.000Z","successor_url":null,"hardware_notes":"Per README: see evidence; training used 8 H20 GPUs.","known_limitations":["256x256 face region; README suggests super-resolution such as GFPGAN for higher output resolution."],"upstream_updated_at":"2025-09-26T05:44:17.000Z"},"categories":["T07"],"tags":["level:advanced","code:python"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://github.com/TMElyralab/MuseTalk","claim":"README: MuseTalk 1.5 released 03/28/2025 and recommended over 1.0; multilingual; single-step latent-space inpainting, 'NOT a diffusion model'; face region is 256x256 and the model was trained at 25fps.","classification":"upstream_claim"},{"url":"https://github.com/TMElyralab/MuseTalk","claim":"README hardware claims: 30fps+ on a Tesla V100; minimum tested RTX 3050 Ti laptop 4GB VRAM taking about 5 minutes for an 8-second fp16 video.","classification":"upstream_claim"},{"url":"https://github.com/TMElyralab/MuseTalk","claim":"README license section: code MIT; trained models available 'for any purpose, even commercially'; whisper, ft-mse-vae and other dependencies keep their own licenses; collected test data is non-commercial research only.","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":"Per README license section.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/TMElyralab/MuseTalk"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README claims weights usable for any purpose including commercially; no separate weights license file was read, and dependencies (whisper, ft-mse-vae) carry their own terms. L07 2026-10-17: license_id set to LicenseRef-MuseTalk-README-weights-statement (README states trained models may be used for any purpose including commercially; no separate weights license file. Named reference so the permission has a stated source.)","hosting":"restricted","component":"model_weights","license_id":"LicenseRef-MuseTalk-README-weights-statement","modification":"unknown","evidence_urls":["https://github.com/TMElyralab/MuseTalk"],"model_training":"unknown","redistribution":"unknown"},{"notes":"README says collected test data is for non-commercial research only.","hosting":"restricted","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/TMElyralab/MuseTalk"],"model_training":"unknown","redistribution":"restricted"}],"attribution":{"origin":"research_agent","upstream_owner":null,"upstream_url":"https://github.com/tmelyralab/musetalk","imported_from":"content/seeds/research/curated/resources.jsonl#tmelyralab--musetalk","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":"tmelyralab--musetalk","name":"TMElyralab/MuseTalk","tags":["level:advanced"],"rights":[{"notes":"Per README license section.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/TMElyralab/MuseTalk"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README claims weights usable for any purpose including commercially; no separate weights license file was read, and dependencies (whisper, ft-mse-vae) carry their own terms. L07 2026-10-17: license_id set to LicenseRef-MuseTalk-README-weights-statement (README states trained models may be used for any purpose including commercially; no separate weights license file. Named reference so the permission has a stated source.)","hosting":"restricted","component":"model_weights","license_id":"LicenseRef-MuseTalk-README-weights-statement","modification":"unknown","evidence_urls":["https://github.com/TMElyralab/MuseTalk"],"model_training":"unknown","redistribution":"unknown"},{"notes":"README says collected test data is for non-commercial research only.","hosting":"restricted","component":"dataset","license_id":null,"modification":"unknown","evidence_urls":["https://github.com/TMElyralab/MuseTalk"],"model_training":"unknown","redistribution":"restricted"}],"archived":false,"evidence":[{"url":"https://github.com/TMElyralab/MuseTalk","claim":"README: MuseTalk 1.5 released 03/28/2025 and recommended over 1.0; multilingual; single-step latent-space inpainting, 'NOT a diffusion model'; face region is 256x256 and the model was trained at 25fps.","classification":"upstream_claim"},{"url":"https://github.com/TMElyralab/MuseTalk","claim":"README hardware claims: 30fps+ on a Tesla V100; minimum tested RTX 3050 Ti laptop 4GB VRAM taking about 5 minutes for an 8-second fp16 video.","classification":"upstream_claim"},{"url":"https://github.com/TMElyralab/MuseTalk","claim":"README license section: code MIT; trained models available 'for any purpose, even commercially'; whisper, ft-mse-vae and other dependencies keep their own licenses; collected test data is non-commercial research only.","classification":"sourced_fact"}],"language":"Python","checked_on":"2026-10-17","usefulness":"Real-time audio-driven lip-sync that inpaints the mouth region in latent space (explicitly not a diffusion model); versions 1.0 and 1.5; README states code and weights are usable commercially. Practical for dubbing existing footage.","source_type":"repository","category_ids":["T07"],"dependencies":["whisper","ft-mse-vae","NVIDIA GPU"],"canonical_url":"https://github.com/TMElyralab/MuseTalk","review_status":"reviewed","hardware_notes":"Per README: see evidence; training used 8 H20 GPUs.","schema_version":"0.1","execution_status":"not_run","inspection_status":"metadata_checked","known_limitations":["256x256 face region; README suggests super-resolution such as GFPGAN for higher output resolution."],"upstream_updated_at":"2025-09-26T05:44:17Z","proposed_next_action":"inspect"},"collector":{"file":"research-results/_inbox/lane-b/T07.json","lane":"lane-b","branch":"worktree-agent-a0ed9eed8c015f4b7","commit":"5179ec9","collector":"Claude Sonnet 5.5 (high), combined lane B (T05-T09), founder-run","file_sha256":"b8ff282ebc83babbdf47f081908275f261a06764c0b09bac925dfb24fb5a35bc","merged_from":[],"original_id":"tmelyralab--musetalk","review_reason":"L07 review 2026-10-17: lane lane-b 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":"tmelyralab--musetalk","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","source_language":"Python","execution_status":"not_run","inspection_status":"metadata_checked","proposed_next_action":"inspect"},"source_schema":"resource-candidate/0.1","original_sha256":"78f4d26bed3e550ef8f56b24eea64e1596dff41958a9520030df03436cb3a14f","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_01M569CP4D7Q8ZXTMJMSWKK6KF","api_url":"https://veyrul.com/v1/records/src_01M569CP4D7Q8ZXTMJMSWKK6KF","created_at":"2026-10-18T01:18:03.906Z","updated_at":"2026-10-18T01:24:44.500Z","last_activity_at":"2026-10-18T01:24:44.500Z"}