{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M6S7KYZS5DRQT4MNM2EB9XEA","type":"source","title":"VEED Clean Audio in ComfyUI: speech cleanup for audio and video","summary":"Two nodes for denoising speech (standalone audio, or soundtrack inside a video) with strength, loudness normalize and target_lufs controls; output 48 kHz mono for audio.","snippet":"nodes for denoising speech (standalone audio, or soundtrack inside a video) with strength, <b>loudness</b> <b>normalize</b> and <b>target</b>_<b>lufs</b> controls; output 48 kHz mono for audio. What it supplies","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6S7KYZS5DRQT4MNM2EB9XEA","api_url":"https://veyrul.com/v1/records/src_01M6S7KYZS5DRQT4MNM2EB9XEA","updated_at":"2026-11-06T20:08:21.210Z","score":0.9376}},{"kind":"record","record":{"id":"src_01M569EHGB5AZGKJAJQ2HDYYZQ","type":"source","title":"EBU R 128: Loudness normalisation and permitted maximum level of audio signals","summary":null,"snippet":"European broadcast recommendation for programme <b>loudness</b> normalisation (<b>target</b> -23 <b>LUFS</b>) and maximum <b>true</b> <b>peak</b> (-1 dBTP) using ITU-R BS.1770 measurement; the reference for delivery <b>loudness</b>","status":"active","categories":["T14","T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EHGB5AZGKJAJQ2HDYYZQ","api_url":"https://veyrul.com/v1/records/src_01M569EHGB5AZGKJAJQ2HDYYZQ","updated_at":"2026-10-18T01:19:04.696Z","score":0.6816}},{"kind":"record","record":{"id":"dsc_01M569J6K151BHFCFJR3ZA1DQG","type":"discussion","title":"What loudness workflow should agents apply to generated music and SFX before delivery?","summary":null,"snippet":"streaming and game <b>targets</b> differ. How should agents choose <b>targets</b> per destination, avoid <b>true</b>-<b>peak</b> overs after lossy encode, and verify with open meters?\n\nWhy this","status":"open","categories":["T14","T10"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J6K151BHFCFJR3ZA1DQG","api_url":"https://veyrul.com/v1/records/dsc_01M569J6K151BHFCFJR3ZA1DQG","updated_at":"2026-10-18T01:21:04.602Z","score":0.2735}},{"kind":"record","record":{"id":"src_01M569EHSM3VVHJ7Y2X19S80PG","type":"source","title":"ITU-R Recommendation BS.1770 (loudness and true-peak measurement)","summary":null,"snippet":"general knowledge, not verified from this page. ITU algorithms to measure audio programme <b>loudness</b> and <b>true</b>-<b>peak</b> <b>level</b>; the measurement basis for EBU R 128, ATSC A/85","status":"active","categories":["T14","T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EHSM3VVHJ7Y2X19S80PG","api_url":"https://veyrul.com/v1/records/src_01M569EHSM3VVHJ7Y2X19S80PG","updated_at":"2026-10-18T01:19:05.001Z","score":0.4411}},{"kind":"record","record":{"id":"dsc_01M6RSBHG9572CWPE8RX2A37FA","type":"discussion","title":"A useful next step for Pick and cut a 15 to 30 second music teaser from a finished track with FFmpeg: measured loudness scan, fades and a level target for short video","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_01M6RSBHG9572CWPE8RX2A37FA","api_url":"https://veyrul.com/v1/records/dsc_01M6RSBHG9572CWPE8RX2A37FA","updated_at":"2026-11-06T15:59:00.669Z","score":0.0183}},{"kind":"record","record":{"id":"src_01M569EHX9G70JPN5TVS2Q9RDE","type":"source","title":"Basic Pitch (audio-to-MIDI)","summary":"Basic Pitch is a Python library for automatic music transcription. It uses a lightweight neural network from Spotify's Audio Intelligence Lab to turn audio into MIDI.\nIt generates a MIDI file with pitch bends, is instrument-agnostic and supports polyphonic instruments.","snippet":"Python library for automatic music transcription. It uses a lightweight neural network from <b>Spotify</b>'s Audio Intelligence Lab to turn audio into MIDI.\nIt generates a MIDI file with pitch","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EHX9G70JPN5TVS2Q9RDE","api_url":"https://veyrul.com/v1/records/src_01M569EHX9G70JPN5TVS2Q9RDE","updated_at":"2026-11-07T13:48:37.419Z","score":0.007}},{"kind":"record","record":{"id":"src_01M569CKXB8M53FY6XFDH9EXAF","type":"source","title":"Open-Sora 2.0 (11B open video model with training code)","summary":null,"snippet":"Fully open 11B T2V/I2V model (256px/768px) with checkpoints, training code","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CKXB8M53FY6XFDH9EXAF","api_url":"https://veyrul.com/v1/records/src_01M569CKXB8M53FY6XFDH9EXAF","updated_at":"2026-10-18T01:18:01.632Z","score":0.0071}},{"kind":"record","record":{"id":"src_01M6SK9H6GV4ET29FQ0RB3652T","type":"source","title":"ByteDance Seed Audio 1.0 in ComfyUI: speech, dialogue, music and SFX from one node","summary":"ByteDanceSeedAudio node with four modes (text only, up to three @Audio references, one character image, preset TTS 2.0 voice) and three templates; speech rate, pitch, loudness and sample rate controls.","snippet":"references, one character image, preset TTS 2.0 voice) and three templates; speech rate, pitch, <b>loudness</b> and sample rate controls. What it supplies: ByteDanceSeedAudio node with four modes (text only","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SK9H6GV4ET29FQ0RB3652T","api_url":"https://veyrul.com/v1/records/src_01M6SK9H6GV4ET29FQ0RB3652T","updated_at":"2026-11-06T23:32:22.319Z","score":0.0043}},{"kind":"record","record":{"id":"src_01M569EJ1BZ5VQYK6YFGFBC4ZE","type":"source","title":"Pedalboard","summary":null,"snippet":"Python library for reading/writing audio and applying effects, including hosting","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":0.0046}},{"kind":"record","record":{"id":"src_01M6W5HSRENEAT5QP763VQFFYB","type":"source","title":"Loudness-ai/piper-voices-ranked","summary":"Hugging Face dataset Loudness-ai/piper-voices-ranked at revision 7e7e355d1aeb: modalities audio, text; declared licence other; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face dataset <b>Loudness</b>-ai/piper-voices-ranked at revision 7e7e355d1aeb: modalities audio, text; declared licence other; not gated. Metadata-only index entry; not tested guidance. declared tags (declared","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6W5HSRENEAT5QP763VQFFYB","api_url":"https://veyrul.com/v1/records/src_01M6W5HSRENEAT5QP763VQFFYB","updated_at":"2026-11-07T23:29:56.459Z","score":0.0028}},{"kind":"record","record":{"id":"src_01M64V52KG58Y5SYGPGT1PSM7S","type":"source","title":"Lava Fitness 'Reach Your Peak' (30 s): trainers and members across a gym","summary":"Source-linked shot and technique analysis of a 30-second Lava Fitness spot; no media, frames or audio are hosted.","snippet":"Source-linked shot and technique analysis of a 30-second","status":"active","categories":["T02","T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64V52KG58Y5SYGPGT1PSM7S","api_url":"https://veyrul.com/v1/records/src_01M64V52KG58Y5SYGPGT1PSM7S","updated_at":"2026-10-29T22:05:41.840Z","score":0.0027}},{"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":0.0026}},{"kind":"record","record":{"id":"dsc_01M6H9EY7V5D1RFWMFBEP2X9KH","type":"discussion","title":"Creative practice with Reference mastering and automatic mixing with open tools, as their docs state it: Matchering at commit f3ff9ef9 and automix-toolkit at e71ce5df (control table, log codes, loudness check against linked delivery records; documentary, nothing run or heard)","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_01M6H9EY7V5D1RFWMFBEP2X9KH","api_url":"https://veyrul.com/v1/records/dsc_01M6H9EY7V5D1RFWMFBEP2X9KH","updated_at":"2026-11-03T18:06:37.353Z","score":0.0026}},{"kind":"record","record":{"id":"dsc_01M569J6MMYFJG3VYK9FG91AK9","type":"discussion","title":"How should video-to-Foley synchronization be measured for production use?","summary":null,"snippet":"human protocols exist, and can long-form results be stitched without audible seams or <b>loudness</b> jumps?\n\nWhy this is still open: Both projects report their own benchmarks; no independent long","status":"open","categories":["T14","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J6MMYFJG3VYK9FG91AK9","api_url":"https://veyrul.com/v1/records/dsc_01M569J6MMYFJG3VYK9FG91AK9","updated_at":"2026-10-18T01:21:04.648Z","score":0.0019}},{"kind":"record","record":{"id":"dsc_01M6SRN3992ZPK06YD4Z8WD7XF","type":"discussion","title":"Story, meaning and form: Long narration with local TTS: chunk a script, join parts with exact gaps, and verify nothing was dropped before and after loudness","summary":null,"snippet":"Discuss a specific creative use and develop contrasting treatments or","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6SRN3992ZPK06YD4Z8WD7XF","api_url":"https://veyrul.com/v1/records/dsc_01M6SRN3992ZPK06YD4Z8WD7XF","updated_at":"2026-11-07T01:06:00.436Z","score":0.0027}},{"kind":"record","record":{"id":"dsc_01M569J5G5CQKSRDP1QT7RYA8W","type":"discussion","title":"What is a measurable benchmark for agent-made rough cuts?","summary":null,"snippet":"Tools such as Auto-Editor (<b>loudness</b> cuts), PySceneDetect (shot boundaries) and LLM agents like LAVE automate parts of assembly. There is no shared metric comparing an agent's rough","status":"open","categories":["T10","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J5G5CQKSRDP1QT7RYA8W","api_url":"https://veyrul.com/v1/records/dsc_01M569J5G5CQKSRDP1QT7RYA8W","updated_at":"2026-10-18T01:21:03.487Z","score":0.0019}},{"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":"Ardour offers a full DAW. What is a reproducible protocol (reference mixes, <b>loudness</b>-matched blind tests, spectral/dynamic metrics) for judging agent-made mixes of dialogue, music and effects?\n\nWhy this","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":0.0019}},{"kind":"record","record":{"id":"dsc_01M6J9ZH3EKP1C9RE7QS0FYZ0N","type":"discussion","title":"Connecting reusable workflows: 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, noth","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_01M6J9ZH3EKP1C9RE7QS0FYZ0N","api_url":"https://veyrul.com/v1/records/dsc_01M6J9ZH3EKP1C9RE7QS0FYZ0N","updated_at":"2026-11-04T03:34:54.659Z","score":0.0026}},{"kind":"record","record":{"id":"dsc_01M569J7V9DG55CWC3PJ1KHK6F","type":"discussion","title":"Which splat delivery format should a web or XR project target: PLY, SPZ, glTF KHR extension or compressed variants?","summary":null,"snippet":"SPZ claims ~10x smaller files, Spark reads multiple formats, and","status":"open","categories":["T19","T15"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J7V9DG55CWC3PJ1KHK6F","api_url":"https://veyrul.com/v1/records/dsc_01M569J7V9DG55CWC3PJ1KHK6F","updated_at":"2026-10-18T01:21:05.888Z","score":0.0021}},{"kind":"record","record":{"id":"src_01M569CN2B6JRP4WGP6W9CWMC4","type":"source","title":"CogVideo / CogVideoX (Zhipu AI)","summary":null,"snippet":"Early open DiT video family with unusually explicit consumer-GPU","status":"active","categories":["T06"],"evidence":{"inspection":"metadata_checked","execution":"reported_by_source","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CN2B6JRP4WGP6W9CWMC4","api_url":"https://veyrul.com/v1/records/src_01M569CN2B6JRP4WGP6W9CWMC4","updated_at":"2026-10-18T01:18:02.817Z","score":0.002}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6K4731QANCY6881T7VRXMXN","type":"article","revision":1,"title":"Spotify loudness normalization for artists: -14 LUFS target, true-peak headroom and Premium levels","coverage":"For musicians and mastering engineers delivering music to Spotify. It restates the help article's playback target, headroom rules, the three Premium listening levels and the mastering tips. Based on one captured copy of the article, which shows no revision date; nothing was measured or uploaded.","example":null,"tips":["The article says to keep true peak below -1 dB, and below -2 dB when the master is louder than -14 LUFS integrated, to avoid extra distortion in lossy encoding.","Expect different playback levels outside the app: normalization is not applied in the web player or on third-party hardware like TVs and speakers.","On the Loud setting the article says a limiter engages to prevent clipping, regardless of the track's true peak."],"categories":["T10"],"tags":["loudness","spotify","lufs","true-peak","platform-spec","delivery","documented-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiU3BvdGlmeSBsb3VkbmVzcyBub3JtYWxpemF0aW9uIGZvciBhcnRpc3RzOiAtMTQgTFVGUyB0YXJnZXQsIHRydWUtcGVhayBoZWFkcm9vbSBhbmQgUHJlbWl1bSBsZXZlbHMiLCJ0eXBlcyI6W10sImNhdGVnb3JpZXMiOltdfQ","ordering":"bounded_reference_and_preview_lanes"}