{"schema":"record/v1","id":"src_01M569EJ2FB5G36599M4BCEEP5","type":"source","revision":1,"etag":"\"r1.s0\"","title":"Stable Audio Open 1.0","summary":null,"status":"active","body":{"text":"","archived":null,"checked_at":"2026-10-17T00:00:00.000Z","parent_url":null,"usefulness":"Open latent-diffusion text-to-audio model (stereo up to 47 s at 44.1 kHz) trained on ~486,500 CC0/CC-BY/CC-Sampling+ recordings from Freesound and FMA; better at sound effects and field recordings than music and cannot generate realistic vocals. Gated under the Stability AI Community License.","source_type":"model","availability":"available","dependencies":["stable-audio-tools"],"source_owner":"Stability AI","canonical_url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","next_check_at":"2026-10-31T00:00:00.000Z","successor_url":null,"hardware_notes":null,"known_limitations":["Max 47 s; weak vocals; English prompts."],"upstream_updated_at":"2025-06-19T21:53:23.000Z"},"categories":["T14"],"tags":["level:established","sound-effects","text-to-audio","foley","ambience","community-license"],"language":"en","visibility":"public","moderation":{"state":"visible","reason":null},"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null,"claims":[{"url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","claim":"Model card: Stability AI Community License, access requires accepting terms; for commercial use the card refers to stability.ai/license.","locator":"model card, license section","classification":"upstream_claim"},{"url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","claim":"Training data: about 486,500 recordings mostly from Freesound plus Free Music Archive, all CC0, CC BY or CC Sampling+; Stability describes copyrighted-music filtering with PANNs, Audible Magic and human review.","locator":"model card, training data","classification":"upstream_claim"},{"url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","claim":"Generates variable-length stereo audio up to 47 seconds at 44.1 kHz using a transformer diffusion model in a compressed latent space with a T5 text encoder; limitations: not able to generate realistic vocals, trained on English descriptions, better at SFX and field recordings than music.","locator":"model card, usage and limitations","classification":"upstream_claim"},{"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":"Gated; Stability AI Community License text not read, commercial terms deferred to stability.ai/license. Training clips need CC attribution per card (separate attribution page not read).","hosting":"restricted","component":"model_weights","license_id":"LicenseRef-Stability-AI-Community","modification":"restricted","evidence_urls":["https://huggingface.co/stabilityai/stable-audio-open-1.0"],"model_training":"unknown","redistribution":"restricted"}],"attribution":{"origin":"research_agent","upstream_owner":"Stability AI","upstream_url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","imported_from":"content/seeds/research/curated/resources.jsonl#stabilityai--stable-audio-open-1.0","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":"stabilityai--stable-audio-open-1.0","name":"Stable Audio Open 1.0","tags":["level:established","sound-effects","text-to-audio","foley","ambience","community-license"],"rights":[{"notes":"Gated; Stability AI Community License text not read, commercial terms deferred to stability.ai/license. Training clips need CC attribution per card (separate attribution page not read).","hosting":"restricted","component":"model_weights","license_id":"LicenseRef-Stability-AI-Community","modification":"restricted","evidence_urls":["https://huggingface.co/stabilityai/stable-audio-open-1.0"],"model_training":"unknown","redistribution":"restricted"}],"evidence":[{"url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","claim":"Model card: Stability AI Community License, access requires accepting terms; for commercial use the card refers to stability.ai/license.","locator":"model card, license section","classification":"upstream_claim"},{"url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","claim":"Training data: about 486,500 recordings mostly from Freesound plus Free Music Archive, all CC0, CC BY or CC Sampling+; Stability describes copyrighted-music filtering with PANNs, Audible Magic and human review.","locator":"model card, training data","classification":"upstream_claim"},{"url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","claim":"Generates variable-length stereo audio up to 47 seconds at 44.1 kHz using a transformer diffusion model in a compressed latent space with a T5 text encoder; limitations: not able to generate realistic vocals, trained on English descriptions, better at SFX and field recordings than music.","locator":"model card, usage and limitations","classification":"upstream_claim"}],"language":null,"checked_on":"2026-10-17","usefulness":"Open latent-diffusion text-to-audio model (stereo up to 47 s at 44.1 kHz) trained on ~486,500 CC0/CC-BY/CC-Sampling+ recordings from Freesound and FMA; better at sound effects and field recordings than music and cannot generate realistic vocals. Gated under the Stability AI Community License.","source_type":"model","category_ids":["T14"],"dependencies":["stable-audio-tools"],"source_owner":"Stability AI","canonical_url":"https://huggingface.co/stabilityai/stable-audio-open-1.0","review_status":"reviewed","schema_version":"0.1","execution_status":"not_run","inspection_status":"source_inspected","known_limitations":["Max 47 s; weak vocals; English prompts."],"upstream_updated_at":"2025-06-19T21:53:23Z","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":"stabilityai--stable-audio-open-1.0","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":"stabilityai--stable-audio-open-1.0","source_file":"content/seeds/research/curated/resources.jsonl","research_side":{"review_status":"reviewed","execution_status":"not_run","inspection_status":"source_inspected","proposed_next_action":"reproduce"},"source_schema":"resource-candidate/0.1","original_sha256":"6866852442ac24bf39c9ec77c16f649eb2bc438cce83691eff49b738c07bab6f","unmapped_fields":["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_01M569EJ2FB5G36599M4BCEEP5","api_url":"https://veyrul.com/v1/records/src_01M569EJ2FB5G36599M4BCEEP5","created_at":"2026-10-18T01:19:05.284Z","updated_at":"2026-10-18T01:19:05.284Z","last_activity_at":"2026-10-18T01:19:05.284Z"}