{"schema":"record/v1","id":"src_01M569EHPJEH7M622J6TZBRJYT","type":"source","revision":2,"etag":"\"r2.s0\"","title":"MMAudio (video-to-audio synthesis, CVPR 2025)","summary":null,"status":"active","body":{"text":"","archived":false,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Generates synchronized audio (Foley, ambience) for video or text using multimodal joint training; about 6 GB GPU memory in 16-bit; default 8-second clips. MIT code, CC-BY-NC checkpoints.","source_type":"repository","availability":"available","dependencies":[],"source_owner":"Ho Kei Cheng et al.","canonical_url":"https://github.com/hkchengrex/mmaudio","next_check_at":"2026-10-31T00:00:00.000Z","successor_url":null,"hardware_notes":"~6 GB GPU memory (16-bit) per README.","known_limitations":["8 s default duration; non-commercial weights."],"upstream_updated_at":"2026-02-23T06:09:19.000Z"},"categories":["T14","T13"],"tags":["level:advanced","video-to-audio","foley","synchronized-audio","cc-by-nc-weights","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/hkchengrex/MMAudio","claim":"README: inference takes around 6GB GPU memory in 16-bit mode; default output and training duration is 8 seconds and large deviations may reduce quality.","locator":"README, requirements and notes","classification":"upstream_claim"},{"url":"https://github.com/hkchengrex/MMAudio","claim":"README: trained on several datasets including AudioSet, Freesound (LAION-audio-630k), VGGSound and others.","locator":"README, training data note","classification":"sourced_fact"},{"url":"https://github.com/hkchengrex/MMAudio","claim":"README License: code MIT; checkpoints released on Hugging Face under CC-BY-NC 4.0.","locator":"README, License","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 per README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/hkchengrex/MMAudio/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README: checkpoints CC-BY-NC 4.0 (non-commercial); training datasets include web-sourced audio with varying rights.","hosting":"restricted","component":"model_weights","license_id":"CC-BY-NC-4.0","modification":"restricted","evidence_urls":["https://github.com/hkchengrex/MMAudio#license"],"model_training":"unknown","redistribution":"restricted"}],"attribution":{"origin":"research_agent","upstream_owner":"Ho Kei Cheng et al.","upstream_url":"https://github.com/hkchengrex/mmaudio","imported_from":"content/seeds/research/curated/resources.jsonl#hkchengrex--mmaudio","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":"hkchengrex--mmaudio","name":"MMAudio (video-to-audio synthesis, CVPR 2025)","tags":["level:advanced","video-to-audio","foley","synchronized-audio","cc-by-nc-weights"],"rights":[{"notes":"MIT per README.","hosting":"permitted","component":"code","license_id":"MIT","modification":"permitted","evidence_urls":["https://github.com/hkchengrex/MMAudio/blob/main/LICENSE"],"model_training":"unknown","redistribution":"permitted"},{"notes":"README: checkpoints CC-BY-NC 4.0 (non-commercial); training datasets include web-sourced audio with varying rights.","hosting":"restricted","component":"model_weights","license_id":"CC-BY-NC-4.0","modification":"restricted","evidence_urls":["https://github.com/hkchengrex/MMAudio#license"],"model_training":"unknown","redistribution":"restricted"}],"archived":false,"evidence":[{"url":"https://github.com/hkchengrex/MMAudio","claim":"README: inference takes around 6GB GPU memory in 16-bit mode; default output and training duration is 8 seconds and large deviations may reduce quality.","locator":"README, requirements and notes","classification":"upstream_claim"},{"url":"https://github.com/hkchengrex/MMAudio","claim":"README: trained on several datasets including AudioSet, Freesound (LAION-audio-630k), VGGSound and others.","locator":"README, training data note","classification":"sourced_fact"},{"url":"https://github.com/hkchengrex/MMAudio","claim":"README License: code MIT; checkpoints released on Hugging Face under CC-BY-NC 4.0.","locator":"README, License","classification":"sourced_fact"}],"language":"Python","checked_on":"2026-10-17","usefulness":"Generates synchronized audio (Foley, ambience) for video or text using multimodal joint training; about 6 GB GPU memory in 16-bit; default 8-second clips. MIT code, CC-BY-NC checkpoints.","source_type":"repository","category_ids":["T14","T13"],"source_owner":"Ho Kei Cheng et al.","canonical_url":"https://github.com/hkchengrex/MMAudio","review_status":"reviewed","hardware_notes":"~6 GB GPU memory (16-bit) per README.","schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","known_limitations":["8 s default duration; non-commercial weights."],"upstream_updated_at":"2026-02-23T06:09:19Z","proposed_next_action":"reproduce"},"collector":{"file":"research-results/_inbox/lane-c/T14.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":"59266c5069dfce174c081d415431cea23c66278e285dc3580ff4f6b17a356e4b","merged_from":[],"original_id":"hkchengrex--mmaudio","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":"hkchengrex--mmaudio","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":"c43a3c19fb8df6f1c7fd2124dbc39daedeffbae833f01732e8a4ff2c94c148ef","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_01M569EHPJEH7M622J6TZBRJYT","api_url":"https://veyrul.com/v1/records/src_01M569EHPJEH7M622J6TZBRJYT","created_at":"2026-10-18T01:19:04.903Z","updated_at":"2026-10-18T01:24:16.665Z","last_activity_at":"2026-10-18T01:24:16.665Z"}