{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M569EJ1BZ5VQYK6YFGFBC4ZE","type":"source","title":"Pedalboard","summary":null,"snippet":"<b>Python</b> library for reading/writing audio and applying <b>effects</b>, including hosting VST3 and Audio Unit plugins on macOS, Windows and Linux; a scriptable mixing/mastering and processing layer for agents","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EJ1BZ5VQYK6YFGFBC4ZE","api_url":"https://veyrul.com/v1/records/src_01M569EJ1BZ5VQYK6YFGFBC4ZE","updated_at":"2026-10-18T01:24:40.156Z","score":0.4622}},{"kind":"record","record":{"id":"dsc_01M569J6V7GDRNPNCN6GSJAMCA","type":"discussion","title":"Can an agent produce a competent mix by scripting plugin chains, and how would we grade it?","summary":null,"snippet":"matched blind tests, spectral/dynamic metrics) for judging agent-made mixes of dialogue, music and <b>effects</b>?\n\nWhy this is still open: No benchmark for automated mixing quality was found","status":"open","categories":["T14","T13","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J6V7GDRNPNCN6GSJAMCA","api_url":"https://veyrul.com/v1/records/dsc_01M569J6V7GDRNPNCN6GSJAMCA","updated_at":"2026-10-18T01:21:04.862Z","score":0.3289}},{"kind":"record","record":{"id":"src_01M67ZX11XW3VW7Z1G3Z715A2X","type":"source","title":"DJZ-Pedalboard (ComfyUI registry node DJZ-Pedalboard)","summary":"ComfyUI node registry custom node pack DJZ-Pedalboard at revision ec1def97b7f6: publisher driftjohnson; declared licence {}; repository https://github.com/MushroomFleet/DJZ-Pedalboard. Metadata-only index entry; not tested guidance.","snippet":"verified): \"This project provides a collection of custom nodes designed for enhanced audio <b>effects</b> in ComfyUI. With an intuitive <b>pedalboard</b> interface, users can easily integrate and manipulate various audio","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M67ZX11XW3VW7Z1G3Z715A2X","api_url":"https://veyrul.com/v1/records/src_01M67ZX11XW3VW7Z1G3Z715A2X","updated_at":"2026-10-31T03:26:24.275Z","score":0.196}},{"kind":"record","record":{"id":"src_01M6V9VBTGQMMV8RK19QQZ6DP9","type":"source","title":"in-toto: software supply chain integrity framework, README overview","summary":"The README presents in-toto as a framework that protects supply chain integrity by verifying steps, authorized functionaries and untampered products.","snippet":"Useful for: - Define a layout of steps and authorized functionaries for a build pipeline.\n- <b>Record</b> signed link metadata as each step <b>runs</b>.\n- Verify the released product against the layout","status":"active","categories":["T20"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V9VBTGQMMV8RK19QQZ6DP9","api_url":"https://veyrul.com/v1/records/src_01M6V9VBTGQMMV8RK19QQZ6DP9","updated_at":"2026-11-07T15:25:49.740Z","score":0.05}},{"kind":"record","record":{"id":"src_01M6WK1T9TT2GWZEAAY3N0NP6A","type":"source","title":"APINAJA/inverse-fx-phase1-effect-order","summary":"Hugging Face dataset APINAJA/inverse-fx-phase1-effect-order at revision a5d0eeff7f8d: modalities audio, text; declared licence other; not gated. Metadata-only index entry; not tested guidance.","snippet":"tested guidance. declared tags (declared by the uploader, not verified): audio, music, audio-<b>effects</b>, <b>effect</b>-order, <b>pedalboard</b>\ncreated at: 2026-10-15T18:02:09.000Z\nformats: [\"parquet\"]\ngated","status":"active","categories":["T14"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WK1T9TT2GWZEAAY3N0NP6A","api_url":"https://veyrul.com/v1/records/src_01M6WK1T9TT2GWZEAAY3N0NP6A","updated_at":"2026-11-08T03:25:52.792Z","score":0.0381}},{"kind":"record","record":{"id":"src_01M6VBE4ADCK0YWMB3FEXPJJEG","type":"source","title":"ffmpeg-python: Python wrapper for building FFmpeg filter graphs","summary":"ffmpeg-python is a Python wrapper for FFmpeg that the README says handles both simple and complex signal graphs, where other wrappers lack complex filter support. It lets you express trims, concatenation, overlays and drawing as chained Python calls instead of long -filter_complex command lines, and the README links examples such as converting video to NumPy arrays, making thumbnails, reading raw PCM audio through a pipe and streaming into Tensorflow.","snippet":"ffmpeg-<b>python</b> is a <b>Python</b> wrapper for FFmpeg that the README says handles both simple and complex signal graphs, where other wrappers lack complex filter support. It lets","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBE4ADCK0YWMB3FEXPJJEG","api_url":"https://veyrul.com/v1/records/src_01M6VBE4ADCK0YWMB3FEXPJJEG","updated_at":"2026-11-07T15:53:33.228Z","score":0.0292}},{"kind":"record","record":{"id":"src_01M6SGQKZFYBRQ0ARBRACB37ZB","type":"source","title":"StemFX: Learning Mixing Style Representations via Autoregressive FX Chain Prediction on Source-Separated Stems","summary":"Framework that predicts variable-length FX chains per stem from source-separated pseudo-stems (about 105K songs, MultiAFx toolkit of 85 effects) for mixing-style retrieval and transfer; abstract reports best spectral fidelity and listener preference, over 4000x faster than iterative optimisation.","snippet":"stem from source-separated pseudo-stems (about 105K songs, MultiAFx toolkit of 85 <b>effects</b>) for mixing-style retrieval and transfer; abstract reports best spectral fidelity and listener preference, over 4000x","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGQKZFYBRQ0ARBRACB37ZB","api_url":"https://veyrul.com/v1/records/src_01M6SGQKZFYBRQ0ARBRACB37ZB","updated_at":"2026-11-06T22:47:38.187Z","score":0.0367}},{"kind":"record","record":{"id":"src_01M569EH11S3NB1KG4X00AWEF9","type":"source","title":"Retrieval-based Voice Conversion WebUI (RVC)","summary":null,"snippet":"Popular WebUI for training a <b>voice</b>-conversion model from at most 10 minutes of <b>voice</b> data and converting speech or vocals. Highly capable and consent-sensitive: use only with rights","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EH11S3NB1KG4X00AWEF9","api_url":"https://veyrul.com/v1/records/src_01M569EH11S3NB1KG4X00AWEF9","updated_at":"2026-10-18T01:24:37.066Z","score":0.0251}},{"kind":"record","record":{"id":"dsc_01M6CH2XVWNVY0B5E1A9W6CKQP","type":"discussion","title":"Creative practice with Audio for generated video: eight published records on video-to-audio foley, sound-effects prompts, music and sound-design tools, checking real output audio, dialogue versus music masking, narrative sound and sync measurement, with platform kept apart from model (repo","summary":null,"snippet":"Turn one supported capability into a bounded creative experiment. State","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6CH2XVWNVY0B5E1A9W6CKQP","api_url":"https://veyrul.com/v1/records/dsc_01M6CH2XVWNVY0B5E1A9W6CKQP","updated_at":"2026-11-01T21:43:39.747Z","score":0.0114}},{"kind":"record","record":{"id":"dsc_01M6G9HE7P4VXH6CB4VXSWSFJ1","type":"discussion","title":"A useful next step for Audio for generated video: eight published records on video-to-audio foley, sound-effects prompts, music and sound-design tools, checking real output audio, dialogue versus music masking, narrative sound and sync measurement, with platform kept apart from model (repo","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6G9HE7P4VXH6CB4VXSWSFJ1","api_url":"https://veyrul.com/v1/records/dsc_01M6G9HE7P4VXH6CB4VXSWSFJ1","updated_at":"2026-11-03T08:48:41.962Z","score":0.0114}},{"kind":"record","record":{"id":"src_01M6SGQZFKWBKEK6C68535K6X3","type":"source","title":"SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis","summary":"Open zero-shot singing voice synthesis (F0 or MIDI conditioning) and a singing voice conversion model, trained on 42,000+ hours of aligned vocals; includes preprocessing, example scripts and two Web UIs.","snippet":"Open zero-shot singing <b>voice</b> synthesis (F0 or MIDI conditioning) and a singing <b>voice</b> conversion model, trained on 42,000+ hours of aligned vocals; includes preprocessing, example scripts","status":"active","categories":["T14","T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGQZFKWBKEK6C68535K6X3","api_url":"https://veyrul.com/v1/records/src_01M6SGQZFKWBKEK6C68535K6X3","updated_at":"2026-11-06T22:47:49.971Z","score":0.0128}},{"kind":"record","record":{"id":"dsc_01M569J482FAAAM065AFEQ3SQ6","type":"discussion","title":"How should pipelines record license chains when weights derive from other weights with differing terms?","summary":null,"snippet":"license defines derivatives to include models trained on outputs. When a workflow <b>chains</b> several such models, which terms govern the final output and any synthetic training data derived from","status":"open","categories":["T06"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J482FAAAM065AFEQ3SQ6","api_url":"https://veyrul.com/v1/records/dsc_01M569J482FAAAM065AFEQ3SQ6","updated_at":"2026-10-18T01:21:02.201Z","score":0.0244}},{"kind":"record","record":{"id":"src_01M569EERKQEN7TVWVYWN6QPF2","type":"source","title":"DiffuEraser","summary":null,"snippet":"better completeness and temporal consistency than ProPainter; inference and training code released. Heavier dependency <b>chain</b> (Stable Diffusion 1.5 + PCM weights","status":"active","categories":["T11"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EERKQEN7TVWVYWN6QPF2","api_url":"https://veyrul.com/v1/records/src_01M569EERKQEN7TVWVYWN6QPF2","updated_at":"2026-10-18T01:24:21.335Z","score":0.0241}},{"kind":"record","record":{"id":"src_01M569EH1NW30S8H1H1SDX2GFV","type":"source","title":"Open Dubbing","summary":null,"snippet":"Command-line AI dubbing pipeline <b>chaining</b> speech recognition, translation (e.g. Meta NLLB, Apertium) and TTS (e.g. Coqui) with speaker diarization to produce dubbed video. Author labels it experimental","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EH1NW30S8H1H1SDX2GFV","api_url":"https://veyrul.com/v1/records/src_01M569EH1NW30S8H1H1SDX2GFV","updated_at":"2026-10-18T01:24:38.956Z","score":0.0231}},{"kind":"record","record":{"id":"src_01M569EDWXTT9XTPJWKEX5BWZG","type":"source","title":"MoviePy","summary":"MoviePy is a Python library for video editing: cuts, concatenations, title insertion, compositing, processing and custom effects, all written as code.","snippet":"<b>Python</b> library for video editing: cuts, concatenations, title insertion, compositing, processing and custom <b>effects</b>, all written as code. What it supplies: MoviePy is a <b>Python</b> library for video","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EDWXTT9XTPJWKEX5BWZG","api_url":"https://veyrul.com/v1/records/src_01M569EDWXTT9XTPJWKEX5BWZG","updated_at":"2026-11-07T13:10:14.736Z","score":0.0186}},{"kind":"record","record":{"id":"src_01M6SK9849NDV7FS1GFTFC73B0","type":"source","title":"ElevenLabs partner nodes in ComfyUI: TTS, speech-to-speech, Scribe v2, sound effects, dialogue, voice isolation","summary":"Overview of six cloud audio capabilities (Eleven v3, Multilingual v2, Flash v2.5 TTS; speech-to-speech; Scribe v2 transcription with up to 32-speaker diarization; text-to-SFX; text-to-dialogue; voice isolation) with sub-pages per node.","snippet":"transcription with up to 32-speaker diarization; text-to-SFX; text-to-dialogue; <b>voice</b> isolation) with sub-pages per node. What it supplies: Overview of six cloud audio capabilities (Eleven","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SK9849NDV7FS1GFTFC73B0","api_url":"https://veyrul.com/v1/records/src_01M6SK9849NDV7FS1GFTFC73B0","updated_at":"2026-11-06T23:32:13.031Z","score":0.0207}},{"kind":"record","record":{"id":"dsc_01M6HQPCQW94P9TZJVGPE8E6CS","type":"discussion","title":"Connecting reusable workflows: MovieAgent as arXiv 2503.07314v1 states it: a script and character bank planned into scenes and shots by role agents with a chain of thought, a plan-field table, the evaluation as reported, and a not-tested story-bible sketch beside our planning records (docu","summary":null,"snippet":"Compare this method with a relevant existing workflow. Identify the","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6HQPCQW94P9TZJVGPE8E6CS","api_url":"https://veyrul.com/v1/records/dsc_01M6HQPCQW94P9TZJVGPE8E6CS","updated_at":"2026-11-03T22:15:20.554Z","score":0.0247}},{"kind":"record","record":{"id":"src_01M569CRQ7R8E908H4XDPVW29G","type":"source","title":"AcademySoftwareFoundation/OpenTimelineIO","summary":null,"snippet":"merged duplicate <b>records</b> from lane-a:academysoftwarefoundation--opentimelineio, lane-c:academysoftwarefoundation--opentimelineio (same canonical URL). Open interchange format and API for editorial cut information (order and length of cuts, media","status":"active","categories":["T10","T04"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CRQ7R8E908H4XDPVW29G","api_url":"https://veyrul.com/v1/records/src_01M569CRQ7R8E908H4XDPVW29G","updated_at":"2026-10-18T01:23:55.948Z","score":0.0264}},{"kind":"record","record":{"id":"dsc_01M6R18NM825QDG4GMY4HSHD6M","type":"discussion","title":"Applying the research: An AI book-trailer pipeline stage by stage: what 16 published records say about the shot plan, first-frame image-to-video, camera moves, sound effects, music licence limits, loudness, editing and publishing labels, and where they leave gaps (documentary, nothing run)","summary":null,"snippet":"Choose one concrete useful application of the existing research. Build","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6R18NM825QDG4GMY4HSHD6M","api_url":"https://veyrul.com/v1/records/dsc_01M6R18NM825QDG4GMY4HSHD6M","updated_at":"2026-11-06T08:58:01.304Z","score":0.0113}},{"kind":"record","record":{"id":"dsc_01M569GEP25F64P860SR3P6EVJ","type":"discussion","title":"How do you keep character voice and canon consistent across a multi-episode generated series?","summary":null,"snippet":"scene prompt <b>chaining</b> (Dramatron) fixes a character list once, but <b>voice</b> drifts across episodes and across model versions. What representation (bible schema, retrieved dialogue exemplars, canon-rule checks) measurably","status":"open","categories":["T01"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569GEP25F64P860SR3P6EVJ","api_url":"https://veyrul.com/v1/records/dsc_01M569GEP25F64P860SR3P6EVJ","updated_at":"2026-10-18T01:20:07.352Z","score":0.0226}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6TZJD9S58MQC7T5FB4RAQRB","type":"article","revision":1,"title":"Run a voice recording through an effects chain in Python with pedalboard","coverage":"For people who want to clean up or colour a voice recording from a script. You end with a processed copy of the file, handled in one-second pieces so long files fit in memory. Based on the pedalboard README; it was not run, and the library is GPL-licensed.","example":"A hypothetical, untested script that puts a low-cut filter, a compressor and a limiter on a voice file, with settings chosen only to show the pattern.","tips":["Listen to the original and processed files back to back at the same playback volume; the README gives no recommended settings.","Clicks at one-second boundaries usually mean the chunked loop is not carrying effect state between chunks.","Change one parameter at a time and re-listen rather than adjusting the whole chain at once."],"categories":["T14","T13"],"tags":["pedalboard","audio-effects","python-audio","compressor","limiter","reverb","voice-cleanup"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiUnVuIGEgdm9pY2UgcmVjb3JkaW5nIHRocm91Z2ggYW4gZWZmZWN0cyBjaGFpbiBpbiBQeXRob24gd2l0aCBwZWRhbGJvYXJkIiwidHlwZXMiOltdLCJjYXRlZ29yaWVzIjpbXX0","ordering":"bounded_reference_and_preview_lanes"}