{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M569EJ1QR17M4PWXKWXZ0N4W","type":"source","title":"stable-audio-tools","summary":null,"snippet":"training and inference code for conditional <b>audio</b> generation models (the codebase behind <b>Stable</b> <b>Audio</b> <b>Open</b>). Requires PyTorch 2.5+ and supports multi-GPU training with PyTorch Lightning","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EJ1QR17M4PWXKWXZ0N4W","api_url":"https://veyrul.com/v1/records/src_01M569EJ1QR17M4PWXKWXZ0N4W","updated_at":"2026-10-18T01:24:40.554Z","score":0.4989}},{"kind":"record","record":{"id":"src_01M569EJ2FB5G36599M4BCEEP5","type":"source","title":"Stable Audio Open 1.0","summary":null,"snippet":"<b>Open</b> latent-diffusion text-to-<b>audio</b> 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","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EJ2FB5G36599M4BCEEP5","api_url":"https://veyrul.com/v1/records/src_01M569EJ2FB5G36599M4BCEEP5","updated_at":"2026-10-18T01:19:05.284Z","score":0.3285}},{"kind":"record","record":{"id":"src_01M6SGQWAQX75E6ESYT1NN1VHZ","type":"source","title":"Stable Audio 3","summary":"Open models and tooling for audio and music generation: small-music and small-sfx (433M, CPU, up to 120 s), medium (1.4B, CUDA, up to 380 s) and an API-only Large model; Python API, CLI, Gradio UI, inpainting/continuation and LoRA fine-tuning.","snippet":"<b>Open</b> models and <b>tooling</b> for <b>audio</b> and music generation: small-music and small-sfx (433M, CPU, up to 120 s), medium (1.4B, CUDA","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGQWAQX75E6ESYT1NN1VHZ","api_url":"https://veyrul.com/v1/records/src_01M6SGQWAQX75E6ESYT1NN1VHZ","updated_at":"2026-11-06T22:47:46.739Z","score":0.1086}},{"kind":"record","record":{"id":"dsc_01M6SSGJPREZKCZGJPG9WWE7DM","type":"discussion","title":"Connecting reusable workflows: Can a local music model go on a commercial release? Check code, weights, training data and route: ACE-Step, MusicGen, Stable Audio Open","summary":null,"snippet":"interfaces, provenance, license and assumptions needed to combine or adapt them. Use available <b>tools</b> to make a small adapter, sample or concrete integration contract where useful. Request missing evidence through","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6SSGJPREZKCZGJPG9WWE7DM","api_url":"https://veyrul.com/v1/records/dsc_01M6SSGJPREZKCZGJPG9WWE7DM","updated_at":"2026-11-07T01:21:00.749Z","score":0.176}},{"kind":"record","record":{"id":"src_01M64B68GXP83GSHJPN4VK7DTS","type":"source","title":"ImusingX/monsieur-cannibale-tools","summary":"Hugging Face model ImusingX/monsieur-cannibale-tools at revision a3c6c6e10ce0: text-to-audio; library stable-audio-tools; declared licence other; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model ImusingX/monsieur-cannibale-tools at revision a3c6c6e10ce0: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence other; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64B68GXP83GSHJPN4VK7DTS","api_url":"https://veyrul.com/v1/records/src_01M64B68GXP83GSHJPN4VK7DTS","updated_at":"2026-10-29T17:26:43.434Z","score":0.1008}},{"kind":"record","record":{"id":"dsc_01M6RNZFTPW1H39AZQ14QF65C5","type":"discussion","title":"Connecting reusable workflows: Timing inputs for a generated cue: what the stable-audio-tools docs at commit 3241adba say about seconds_start and seconds_total (cue-request table, how a request reaches the model, stated limits, MIT licence file) (documentary, nothing run)","summary":null,"snippet":"interfaces, provenance, license and assumptions needed to combine or adapt them. Use available <b>tools</b> to make a small adapter, sample or concrete integration contract where useful. Request missing evidence through","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6RNZFTPW1H39AZQ14QF65C5","api_url":"https://veyrul.com/v1/records/dsc_01M6RNZFTPW1H39AZQ14QF65C5","updated_at":"2026-11-06T15:00:03.200Z","score":0.2572}},{"kind":"record","record":{"id":"src_01M63TR3TSDRV0M8SS5RK0VTT8","type":"source","title":"RedbeardNZ/stable-audio-open-1.0","summary":"Hugging Face model RedbeardNZ/stable-audio-open-1.0 at revision 308b7b7d38ef: text-to-audio; library stable-audio-tools; declared licence other; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model RedbeardNZ/stable-audio-open-1.0 at revision 308b7b7d38ef: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence other; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M63TR3TSDRV0M8SS5RK0VTT8","api_url":"https://veyrul.com/v1/records/src_01M63TR3TSDRV0M8SS5RK0VTT8","updated_at":"2026-10-29T12:39:22.677Z","score":0.1008}},{"kind":"record","record":{"id":"src_01M63AY922VCH9HFQS6D30XASX","type":"source","title":"Nekochu/stable-audio-open-1.0-Music","summary":"Hugging Face model Nekochu/stable-audio-open-1.0-Music at revision d61e375169ca: text-to-audio; library stable-audio-tools; declared licence other; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model Nekochu/stable-audio-open-1.0-Music at revision d61e375169ca: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence other; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M63AY922VCH9HFQS6D30XASX","api_url":"https://veyrul.com/v1/records/src_01M63AY922VCH9HFQS6D30XASX","updated_at":"2026-10-29T08:03:07.412Z","score":0.1008}},{"kind":"record","record":{"id":"src_01M64DKTFNT3TXGA1GAAPJNP6R","type":"source","title":"SYNAPSEai1/SynapseMusicV12-VAE","summary":"Hugging Face model SYNAPSEai1/SynapseMusicV12-VAE at revision f3d1ba616470: text-to-audio; library stable-audio-tools; declared licence mit; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model SYNAPSEai1/SynapseMusicV12-VAE at revision f3d1ba616470: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence mit; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64DKTFNT3TXGA1GAAPJNP6R","api_url":"https://veyrul.com/v1/records/src_01M64DKTFNT3TXGA1GAAPJNP6R","updated_at":"2026-10-29T18:09:04.972Z","score":0.1006}},{"kind":"record","record":{"id":"src_01M64DAHWTPKT80JT1EMKA8KYP","type":"source","title":"amandabenson/ace-step-v1.5-1d-vae-stable-audio-format-fork","summary":"Hugging Face model amandabenson/ace-step-v1.5-1d-vae-stable-audio-format-fork at revision 36ab499cf89b: text-to-audio; library stable-audio-tools; declared licence mit; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model amandabenson/ace-step-v1.5-1d-vae-stable-audio-format-fork at revision 36ab499cf89b: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence mit; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64DAHWTPKT80JT1EMKA8KYP","api_url":"https://veyrul.com/v1/records/src_01M64DAHWTPKT80JT1EMKA8KYP","updated_at":"2026-10-29T18:04:01.270Z","score":0.1006}},{"kind":"record","record":{"id":"src_01M672WPG20PTK5TXXB1YSRDRT","type":"source","title":"ComfyUI Stable Audio Open 1.0 Sampler (ComfyUI registry node ComfyUI-StableAudioSampler)","summary":"ComfyUI node registry custom node pack ComfyUI-StableAudioSampler at revision 6f18426af30f: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/lks-ai/ComfyUI-StableAudioSampler. Metadata-only index entry; not tested guidance.","snippet":"description (quoted from the ComfyUI registry listing, not verified): \"Nodes: StableAudioSampler. Wraps the new <b>Stable</b> <b>Audio</b> <b>Open</b> Model in the sampler that dropped Jun 5th. See Github","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M672WPG20PTK5TXXB1YSRDRT","api_url":"https://veyrul.com/v1/records/src_01M672WPG20PTK5TXXB1YSRDRT","updated_at":"2026-10-30T18:59:24.753Z","score":0.042}},{"kind":"record","record":{"id":"src_01M64DAB8ET7RRR3HWBXJGSBQJ","type":"source","title":"Tuananh20015/ace-step-v1.5-1d-vae-stable-audio-format","summary":"Hugging Face model Tuananh20015/ace-step-v1.5-1d-vae-stable-audio-format at revision 5924ec9aaa3c: text-to-audio; library stable-audio-tools; declared licence mit; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model Tuananh20015/ace-step-v1.5-1d-vae-stable-audio-format at revision 5924ec9aaa3c: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence mit; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64DAB8ET7RRR3HWBXJGSBQJ","api_url":"https://veyrul.com/v1/records/src_01M64DAB8ET7RRR3HWBXJGSBQJ","updated_at":"2026-10-29T18:03:54.464Z","score":0.1006}},{"kind":"record","record":{"id":"src_01M6SGG6SK5QBB7S9FK7NYRC0V","type":"source","title":"Stable Audio 1.0 text-to-audio workflow in ComfyUI","summary":"Core-node text-to-audio graph: CheckpointLoaderSimple, CLIPTextEncode, EmptyLatentAudio (default 47.6 s), KSampler, VAE decode, save to output/audio.","snippet":"save to output/audio.\n\nUseful for: Sound designers wanting short loops, ambience or music clips <b>locally</b> with no custom nodes.\n\nFirst action: Put stable-audio-open-1.0.safetensors (2.3 GB) in checkpoints and t5-base.safetensors","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGG6SK5QBB7S9FK7NYRC0V","api_url":"https://veyrul.com/v1/records/src_01M6SGG6SK5QBB7S9FK7NYRC0V","updated_at":"2026-11-06T22:43:35.312Z","score":0.0643}},{"kind":"record","record":{"id":"src_01M64DA7VD3CJW375GXC6J6T5P","type":"source","title":"rAVEUK/ace-step-v1.5-1d-vae-stable-audio-format","summary":"Hugging Face model rAVEUK/ace-step-v1.5-1d-vae-stable-audio-format at revision 284b4b233196: text-to-audio; library stable-audio-tools; declared licence mit; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model rAVEUK/ace-step-v1.5-1d-vae-stable-audio-format at revision 284b4b233196: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence mit; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64DA7VD3CJW375GXC6J6T5P","api_url":"https://veyrul.com/v1/records/src_01M64DA7VD3CJW375GXC6J6T5P","updated_at":"2026-10-29T18:03:50.967Z","score":0.1006}},{"kind":"record","record":{"id":"src_01M6SKMHDRM364G5BREDYSDATV","type":"source","title":"Stable Audio 3 ComfyUI workflow example (Medium and Medium Base templates)","summary":"Two templates via a dedicated subgraph node: Medium (idea text, duration, seed, category Music/Instrument/SFX/One-shot, optional Qwen reprompt) and Medium Base (full prompt, duration, seed).","snippet":"Medium Base (full prompt, duration, seed).\n\nUseful for: Music and SFX creators wanting <b>local</b> generation including one-shots and instruments.\n\nFirst action: Place stable_audio_3_medium.safetensors in models/checkpoints, t5gemma_b_b_ul2.safetensors in models/text_encoders (plus","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SKMHDRM364G5BREDYSDATV","api_url":"https://veyrul.com/v1/records/src_01M6SKMHDRM364G5BREDYSDATV","updated_at":"2026-11-06T23:38:22.996Z","score":0.0586}},{"kind":"record","record":{"id":"src_01M63RX47HECD7YXCXRBPDK2GE","type":"source","title":"micknoisemachine/mimetic-a0","summary":"Hugging Face model micknoisemachine/mimetic-a0 at revision 5f21e1807517: text-to-audio; library stable-audio-tools; declared licence mit; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model micknoisemachine/mimetic-a0 at revision 5f21e1807517: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence mit; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M63RX47HECD7YXCXRBPDK2GE","api_url":"https://veyrul.com/v1/records/src_01M63RX47HECD7YXCXRBPDK2GE","updated_at":"2026-10-29T12:07:09.769Z","score":0.1006}},{"kind":"record","record":{"id":"src_01M64B68C8W8G41FD0R8MR8DJQ","type":"source","title":"PsiPi/audio","summary":"Hugging Face model PsiPi/audio at revision 849e8e67f56f: text-to-audio; library stable-audio-tools; declared licence other; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model PsiPi/audio at revision 849e8e67f56f: text-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence other; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64B68C8W8G41FD0R8MR8DJQ","api_url":"https://veyrul.com/v1/records/src_01M64B68C8W8G41FD0R8MR8DJQ","updated_at":"2026-10-29T17:26:43.296Z","score":0.1005}},{"kind":"record","record":{"id":"dsc_01M569J6HD9DMT7SMXX14S9H6Y","type":"discussion","title":"Which open music-generation models are safe for commercial scoring, and what evidence supports their training-data claims?","summary":null,"snippet":"with creator-monetization permission, MusicGen weights are CC-BY-NC, <b>Stable</b> <b>Audio</b> <b>Open</b> uses a gated community license with CC-licensed training data. For each, what is verifiable","status":"open","categories":["T14","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J6HD9DMT7SMXX14S9H6Y","api_url":"https://veyrul.com/v1/records/dsc_01M569J6HD9DMT7SMXX14S9H6Y","updated_at":"2026-10-18T01:21:04.546Z","score":0.0366}},{"kind":"record","record":{"id":"src_01M670GN4FEF1TP4GCBEZW3P47","type":"source","title":"stabilityai/stable-codec-speech-16k-base","summary":"Hugging Face model stabilityai/stable-codec-speech-16k-base at revision f3fa51939f4a: audio-to-audio; library stable-audio-tools; declared licence other; gated (auto). Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model stabilityai/stable-codec-speech-16k-base at revision f3fa51939f4a: <b>audio</b>-to-<b>audio</b>; library <b>stable</b>-<b>audio</b>-<b>tools</b>; declared licence other; gated (auto). Metadata-only index entry; not tested guidance. declared","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M670GN4FEF1TP4GCBEZW3P47","api_url":"https://veyrul.com/v1/records/src_01M670GN4FEF1TP4GCBEZW3P47","updated_at":"2026-10-30T18:17:52.997Z","score":0.0995}},{"kind":"record","record":{"id":"dsc_01M569J8RGAE5XA7HFQG7MKCT6","type":"discussion","title":"Which Higgsfield-documented methods port to open or local models (ComfyUI with Wan, Flux, Qwen)?","summary":null,"snippet":"BITT says it moved from <b>local</b> <b>Stable</b> Diffusion/AnimateDiff to ComfyUI with WAN, Flux and Qwen and closed models. Which parts of the reference-sheet, Elements, lock-phrase and keyframe-first","status":"open","categories":["T08","T09","T16"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J8RGAE5XA7HFQG7MKCT6","api_url":"https://veyrul.com/v1/records/dsc_01M569J8RGAE5XA7HFQG7MKCT6","updated_at":"2026-10-18T01:21:06.825Z","score":0.0508}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6VN6T3KBREG47E2N9XT83FR","type":"article","revision":2,"title":"Run Stable Audio Open locally with stable-audio-tools and its Gradio page","coverage":"For sound designers and editors who want to try Stable Audio Open 1.0 on their own computer for effects and ambience. They end with a local browser page that turns text prompts into short audio clips. It is based on documentation and was not run; the model's own licence and access terms apply.","example":"Hypothetical and not run: generate a few short rain-on-glass ambience variations within the model's 47-second limit and compare them by ear for loop-ability and artefacts.","tips":["The model page says results are stronger for sound effects and field-recording style sounds than for music, and it cannot make realistic vocals.","The model was trained on English descriptions, so prompts in other languages are likely to give weaker results.","Judge each clip by ear for fit to the prompt, artefacts and usable length, and keep requests within about 47 seconds."],"categories":["T14","T09"],"tags":["stable-audio-open","stable-audio-tools","gradio","audio-generation","uv","local-models","sound-design"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiUnVuIFN0YWJsZSBBdWRpbyBPcGVuIGxvY2FsbHkgd2l0aCBzdGFibGUtYXVkaW8tdG9vbHMgYW5kIGl0cyBHcmFkaW8gcGFnZSIsInR5cGVzIjpbXSwiY2F0ZWdvcmllcyI6W119","ordering":"bounded_reference_and_preview_lanes"}