{"schema":"catalog-search/v2","items":[{"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":"uses a lightweight neural network from Spotify's <b>Audio</b> Intelligence Lab to <b>turn</b> <b>audio</b> into <b>MIDI</b>.\nIt generates a <b>MIDI</b> file with <b>pitch</b> bends","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":1.7853}},{"kind":"record","record":{"id":"src_01M6SAXKBMFCZX86XXHM7PE87V","type":"source","title":"pretty_midi","summary":"Utility classes for loading, editing and inspecting MIDI data as Python objects; can synthesize audio from the MIDI (sine waves in the README example, or through the fluidsynth program).","snippet":"Python objects; can synthesize <b>audio</b> from the <b>MIDI</b> (sine waves in the <b>README</b> example, or through the fluidsynth program). What it supplies: Utility classes for loading, editing","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SAXKBMFCZX86XXHM7PE87V","api_url":"https://veyrul.com/v1/records/src_01M6SAXKBMFCZX86XXHM7PE87V","updated_at":"2026-11-06T21:06:02.697Z","score":0.6886}},{"kind":"record","record":{"id":"src_01M6V9P5BEVQ56J0TCWPF9ZH6W","type":"source","title":"Mido: MIDI objects for Python, README overview","summary":"The README presents Mido as a Python library for working with MIDI messages, ports and files.","snippet":"<b>README</b> presents Mido as a Python library for working with <b>MIDI</b> messages, ports and files. What it supplies: The <b>README</b> presents Mido as a Python library for working with","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V9P5BEVQ56J0TCWPF9ZH6W","api_url":"https://veyrul.com/v1/records/src_01M6V9P5BEVQ56J0TCWPF9ZH6W","updated_at":"2026-11-07T15:22:59.274Z","score":0.6557}},{"kind":"record","record":{"id":"src_01M6SDPJNT32P625PXV8EVMPDD","type":"source","title":"Music To MIDI","summary":"Local-first audio-to-MIDI converter with CLI batch mode for multi-track transcription, optional lyrics embedding and SoundFont rendering.","snippet":"<b>audio</b>-to-<b>MIDI</b> converter with CLI batch mode for multi-track transcription, <b>optional</b> lyrics embedding and SoundFont rendering. What it supplies: Local-first <b>audio</b>-to-<b>MIDI</b>","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SDPJNT32P625PXV8EVMPDD","api_url":"https://veyrul.com/v1/records/src_01M6SDPJNT32P625PXV8EVMPDD","updated_at":"2026-11-06T21:54:38.348Z","score":0.6515}},{"kind":"record","record":{"id":"src_01M6V5KWV5K3RK9H873CT6Y3V3","type":"source","title":"FluidSynth: real-time SoundFont software synthesizer, README overview","summary":"The README presents FluidSynth as a real-time software synthesizer that renders audio from MIDI using SoundFont files.","snippet":"<b>README</b> presents FluidSynth as a real-time software synthesizer that renders <b>audio</b> from <b>MIDI</b> using SoundFont files. What it supplies: The <b>README</b> presents FluidSynth as a real-time","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V5KWV5K3RK9H873CT6Y3V3","api_url":"https://veyrul.com/v1/records/src_01M6V5KWV5K3RK9H873CT6Y3V3","updated_at":"2026-11-07T14:11:50.720Z","score":0.5545}},{"kind":"record","record":{"id":"src_01M6V3K1FFVQEHE8TGB0T1R0Q2","type":"source","title":"Pandoc: universal markup converter, README overview","summary":"The README describes Pandoc as a Haskell library for converting from one markup format to another, and a command-line tool that uses it.","snippet":"<b>README</b> describes Pandoc as a Haskell library for converting from one markup format to another, and a command-line tool that uses it. What it supplies: The <b>README</b> describes Pandoc","status":"active","categories":["T01"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V3K1FFVQEHE8TGB0T1R0Q2","api_url":"https://veyrul.com/v1/records/src_01M6V3K1FFVQEHE8TGB0T1R0Q2","updated_at":"2026-11-07T13:36:25.549Z","score":0.3377}},{"kind":"record","record":{"id":"src_01M66QAY3TPQ6QJDZ5JPG5DV2S","type":"source","title":"ComfyUI MIDI Edit (ComfyUI registry node ComfyUI-MIDI-Edit)","summary":"ComfyUI node registry custom node pack ComfyUI-MIDI-Edit at revision 8d0cc21396e8: latest version 3.4.2; publisher ahkimkoo; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/ahkimkoo/ComfyUI-MIDI-Edit. Metadata-only index entry; not tested guidance.","snippet":"ComfyUI node registry custom node pack ComfyUI-<b>MIDI</b>-Edit at revision 8d0cc21396e8: latest version 3.4.2; publisher ahkimkoo; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/ahkimkoo/ComfyUI-MIDI-Edit. Metadata-only index entry","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66QAY3TPQ6QJDZ5JPG5DV2S","api_url":"https://veyrul.com/v1/records/src_01M66QAY3TPQ6QJDZ5JPG5DV2S","updated_at":"2026-10-30T15:37:28.398Z","score":0.5175}},{"kind":"record","record":{"id":"src_01M6V3Z1ABJQPBYGCF0FRVRMHB","type":"source","title":"lm-evaluation-harness: unified framework for testing generative language models, README overview","summary":"The README says the project provides a unified framework to test generative language models on a large number of different evaluation tasks.","snippet":"<b>README</b> <b>says</b> the project provides a unified framework to test generative language models on a large number of different evaluation tasks. What it supplies: The <b>README</b> <b>says</b> the project provides","status":"active","categories":["T20"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V3Z1ABJQPBYGCF0FRVRMHB","api_url":"https://veyrul.com/v1/records/src_01M6V3Z1ABJQPBYGCF0FRVRMHB","updated_at":"2026-11-07T13:42:58.599Z","score":0.3262}},{"kind":"record","record":{"id":"src_01M6VQZEFR4NQR4W0YF3J5CQKA","type":"source","title":"Bark: transformer text-to-audio model for speech and sound, README overview","summary":"The README presents Bark as a generative text-to-audio model for speech, music and sound, not a conventional TTS system.","snippet":"<b>README</b> presents Bark as a generative text-to-<b>audio</b> model for speech, music and sound, not a conventional TTS system. What it supplies: The <b>README</b> presents Bark","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VQZEFR4NQR4W0YF3J5CQKA","api_url":"https://veyrul.com/v1/records/src_01M6VQZEFR4NQR4W0YF3J5CQKA","updated_at":"2026-11-07T19:32:43.606Z","score":0.2987}},{"kind":"record","record":{"id":"src_01M6V7Q96RFM64B03MRC47H7XN","type":"source","title":"RIFE: real-time intermediate flow estimation for video frame interpolation","summary":"RIFE is the implementation of the ECCV 2022 paper on real-time intermediate flow estimation for video frame interpolation. The README says the model runs at 30+ FPS for 2X 720p interpolation on a 2080Ti GPU and supports arbitrary-timestep interpolation between a pair of images.","snippet":"ECCV 2022 paper on real-time intermediate flow estimation for video frame interpolation. The <b>README</b> <b>says</b> the model runs at 30+ FPS for 2X 720p interpolation on a 2080Ti","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V7Q96RFM64B03MRC47H7XN","api_url":"https://veyrul.com/v1/records/src_01M6V7Q96RFM64B03MRC47H7XN","updated_at":"2026-11-07T14:48:38.840Z","score":0.3084}},{"kind":"record","record":{"id":"src_01M6TVMWZCHMNNKBF73T0QB2HE","type":"source","title":"librosa: Python library for audio and music signal processing, README overview","summary":"The README describes librosa as a Python library for audio and music signal processing that provides the foundational algorithms and tools required for building music information retrieval (MIR) systems.","snippet":"<b>README</b> describes librosa as a Python library for <b>audio</b> and music signal processing that provides the foundational algorithms and tools required for building music information retrieval (MIR) systems. What","status":"active","categories":["T14"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6TVMWZCHMNNKBF73T0QB2HE","api_url":"https://veyrul.com/v1/records/src_01M6TVMWZCHMNNKBF73T0QB2HE","updated_at":"2026-11-07T11:17:37.867Z","score":0.3106}},{"kind":"record","record":{"id":"dsc_01M6SA0AWPQWMKRYR7M0VW0ARJ","type":"discussion","title":"Connecting reusable workflows: Syncing a subtitle file to its soundtrack with ffsubsync: what the README states on usage, sync options and limits, checked against two records","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_01M6SA0AWPQWMKRYR7M0VW0ARJ","api_url":"https://veyrul.com/v1/records/dsc_01M6SA0AWPQWMKRYR7M0VW0ARJ","updated_at":"2026-11-06T20:50:00.633Z","score":0.3219}},{"kind":"record","record":{"id":"dsc_01M6R9Z0HYDCDKREWR1XHTDQX4","type":"discussion","title":"Connecting reusable workflows: Syncing a subtitle file to its soundtrack with ffsubsync: what the README states on usage, sync options and limits, checked against two records","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_01M6R9Z0HYDCDKREWR1XHTDQX4","api_url":"https://veyrul.com/v1/records/dsc_01M6R9Z0HYDCDKREWR1XHTDQX4","updated_at":"2026-11-06T11:30:01.691Z","score":0.3219}},{"kind":"record","record":{"id":"dsc_01M6FYSHG78GDAXM1H5H245M2W","type":"discussion","title":"Story, meaning and form: gltfjsx repository documentation (gltfjsx): what its readme, LICENSE and file listing state about the command-line tool that turns GLTF assets into react-three-fiber components, its usage and options, requirements and MIT license text (3 of 3 files, nothing run)","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_01M6FYSHG78GDAXM1H5H245M2W","api_url":"https://veyrul.com/v1/records/dsc_01M6FYSHG78GDAXM1H5H245M2W","updated_at":"2026-11-03T05:40:54.797Z","score":0.3256}},{"kind":"record","record":{"id":"src_01M569EGVGE98442AG0PZ67B35","type":"source","title":"pyannote.audio (speaker diarization toolkit)","summary":"The README says pyannote.audio is an open-source toolkit written in Python for speaker diarization, based on PyTorch, with pretrained models and pipelines.","snippet":"<b>README</b> <b>says</b> pyannote.audio is an open-source toolkit written in Python for speaker diarization, based on PyTorch, with pretrained models and pipelines. What it supplies: The <b>README</b> <b>says</b> pyannote.audio","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EGVGE98442AG0PZ67B35","api_url":"https://veyrul.com/v1/records/src_01M569EGVGE98442AG0PZ67B35","updated_at":"2026-11-07T13:39:46.096Z","score":0.3216}},{"kind":"record","record":{"id":"src_01M6WCJ4AWT80BD6CCWMNCJPNB","type":"source","title":"Stable Fast 3D: single-image 3D mesh reconstruction with UV unwrapping","summary":"The official codebase for Stable Fast 3D (SF3D), an open-source model for fast feed-forward 3D mesh reconstruction from a single image. The README says it builds on TripoSR and adds techniques to produce meshes without artefacts, textures with UV unwrapping, and removal of baked-in lighting from the colours. Running python run.py on an image writes a GLB file to the output folder, and the README states the default takes about 6 GB of VRAM for a single image.","snippet":"source model for fast feed-forward 3D mesh reconstruction from a single image. The <b>README</b> <b>says</b> it builds on TripoSR and adds techniques to produce meshes without artefacts, textures with","status":"active","categories":["T15","T19"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WCJ4AWT80BD6CCWMNCJPNB","api_url":"https://veyrul.com/v1/records/src_01M6WCJ4AWT80BD6CCWMNCJPNB","updated_at":"2026-11-08T01:32:27.325Z","score":0.3538}},{"kind":"record","record":{"id":"src_01M569EGKB12MJ1XPDKRGFZY25","type":"source","title":"WhisperX","summary":"The README says the repository provides fast automatic speech recognition (70x realtime with large-v2) with word-level timestamps and speaker diarization.","snippet":"<b>README</b> <b>says</b> the repository provides fast automatic speech recognition (70x realtime with large-v2) with word-level timestamps and speaker diarization. What it supplies: The <b>README</b> <b>says</b> the repository provides","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EGKB12MJ1XPDKRGFZY25","api_url":"https://veyrul.com/v1/records/src_01M569EGKB12MJ1XPDKRGFZY25","updated_at":"2026-11-07T13:36:28.201Z","score":0.3033}},{"kind":"record","record":{"id":"src_01M6WCMY3409K4BGEH8T95TW1E","type":"source","title":"StreamingT2V / StreamingSVD: autoregressive long video generation","summary":"The README presents StreamingSVD, an autoregressive method that turns Stable Video Diffusion into a long video generator for text-to-video and image-to-video, as part of the StreamingT2V family (accepted at CVPR 2025). The inference script runs an image-to-video pipeline that includes video enhancement with randomised blending and frame interpolation. A memory-optimised version was released in November 2024.","snippet":"<b>README</b> presents StreamingSVD, an autoregressive method that <b>turns</b> Stable Video Diffusion into a long video generator for text-to-video and image-to-video, as part of the StreamingT2V family","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WCMY3409K4BGEH8T95TW1E","api_url":"https://veyrul.com/v1/records/src_01M6WCMY3409K4BGEH8T95TW1E","updated_at":"2026-11-08T01:33:59.233Z","score":0.316}},{"kind":"record","record":{"id":"src_01M6V01BW2Y6DGYDFVMQK60QZM","type":"source","title":"Babylon.js: JavaScript 3D engine install routes, quick-start scene and learning tools","summary":"The README does not define the project in prose; it starts with a playground link for trying the Babylon.js API with many samples, and its usage example builds a 3D scene on a canvas with an engine, a camera, a light, a sphere and a ground.\nIt points to the website for the complete list of supported features.","snippet":"<b>README</b> does not define the project in prose; it starts with a playground link for trying the Babylon.js API with many samples, and its usage example builds a 3D scene","status":"active","categories":["T15"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V01BW2Y6DGYDFVMQK60QZM","api_url":"https://veyrul.com/v1/records/src_01M6V01BW2Y6DGYDFVMQK60QZM","updated_at":"2026-11-07T12:34:20.640Z","score":0.3117}},{"kind":"record","record":{"id":"src_01M6W7JNQ4P7SJT7P69SW752JM","type":"source","title":"DSPy: framework for programming rather than prompting language models, README overview","summary":"The README presents DSPy as a way to build LM systems from Python modules and let optimizers tune prompts and weights.","snippet":"<b>README</b> presents DSPy as a way to build LM systems from Python modules and let optimizers tune prompts and weights. What it supplies: The <b>README</b> presents DSPy","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6W7JNQ4P7SJT7P69SW752JM","api_url":"https://veyrul.com/v1/records/src_01M6W7JNQ4P7SJT7P69SW752JM","updated_at":"2026-11-08T00:05:22.242Z","score":0.2971}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6H8WBT8KJ4J7Y388D9GJ2PP","type":"article","revision":1,"title":"What the Basic Pitch README says about turning audio into MIDI: inputs, outputs, options and limits","coverage":"For musicians and producers weighing an audio-to-MIDI tool, this note lays out what the Basic Pitch documentation says about accepted audio, output files, runtime choices and the allowed note range. It is based on three repository files at a fixed commit; nothing was installed, run or heard.","example":null,"tips":["Work from one instrument at a time; the documentation says the tool performs best on a single instrument.","Stereo audio is mixed down to mono and everything is resampled before analysis, so keep that in mind when comparing against your original.","The documentation does not claim the MIDI needs no editing, so plan to check every note and bend in your DAW."],"categories":["T20","T01"],"tags":["basic-pitch","audio-to-midi","note-transcription","pitch-bend","polyphonic","daw-workflow","apache-2-0","documented-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiV2hhdCB0aGUgQmFzaWMgUGl0Y2ggUkVBRE1FIHNheXMgYWJvdXQgdHVybmluZyBhdWRpbyBpbnRvIE1JREk6IGlucHV0cywgb3V0cHV0cywgb3B0aW9ucyBhbmQgbGltaXRzIiwidHlwZXMiOltdLCJjYXRlZ29yaWVzIjpbXX0","ordering":"bounded_reference_and_preview_lanes"}