{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M6804WCFRRCP1A3V6DSJWJR5","type":"source","title":"mila-ai4h/mid-space","summary":"Hugging Face dataset mila-ai4h/mid-space at revision 166070c955c7: modalities image; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"arxiv:2503.01894\ndeclared tags (declared by the uploader, not verified): art, city, public, visualization, <b>alignment</b>, <b>montreal</b>, urban, spaces\ncreated at: 2024-12-09T20:01:29.000Z\nformats","status":"active","categories":["T05"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6804WCFRRCP1A3V6DSJWJR5","api_url":"https://veyrul.com/v1/records/src_01M6804WCFRRCP1A3V6DSJWJR5","updated_at":"2026-10-31T03:30:41.638Z","score":0.0428}},{"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":0.0415}},{"kind":"record","record":{"id":"src_01M668KGCACQPVAKVSPB9V5RKM","type":"source","title":"ComfyUI-Audio-Srt-Aligner (ComfyUI registry node ComfyUI-Audio-Srt-Aligner)","summary":"ComfyUI node registry custom node pack ComfyUI-Audio-Srt-Aligner at revision 4a2339baba84: latest version 1.1.0; publisher ahkimkoo; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/ahkimkoo/ComfyUI-Audio-Srt-Aligner. Metadata-only index entry; not tested guidance.","snippet":"<b>alignment</b> with multiple engines: LIS token matching, stable-ts cross-attention, and Qwen3 <b>forced</b> <b>alignment</b>. Supports faster-whisper, UVR5 vocal separation, and video subtitle overlay rendering.\"\ncreated","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M668KGCACQPVAKVSPB9V5RKM","api_url":"https://veyrul.com/v1/records/src_01M668KGCACQPVAKVSPB9V5RKM","updated_at":"2026-10-30T11:20:00.614Z","score":0.0384}},{"kind":"record","record":{"id":"src_01M569GBH740TD69GVDK3QGE58","type":"source","title":"ink (inkle's interactive narrative scripting language)","summary":null,"snippet":"licensed markup language and runtime (C#, with JS ports elsewhere) for branching, stateful interactive <b>narrative</b>, used for commercial games; the WritingWithInk guide is the standard tutorial for weaves, knots, diverts","status":"active","categories":["T18","T01"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569GBH740TD69GVDK3QGE58","api_url":"https://veyrul.com/v1/records/src_01M569GBH740TD69GVDK3QGE58","updated_at":"2026-10-18T01:20:04.123Z","score":0.0296}},{"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":"pipeline adding batched inference (README: 70x realtime with large-v2 via faster-whisper), wav2vec2 <b>forced</b> <b>alignment</b> for word-level timestamps, and pyannote speaker diarization. Practical for timed dialogue transcripts","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":0.0232}},{"kind":"record","record":{"id":"src_01M6SGR1JSDC75GN6G05RXYZT1","type":"source","title":"HeartMuLa: A Family of Open Sourced Music Foundation Models","summary":"Open lyrics-and-tags song generation (3B released), a 12.5 Hz codec, a Whisper-based lyrics transcriber and an audio-text alignment model; example script, low-memory options and a separate MuLaCover cover model noted in news.","snippet":"released), a 12.5 Hz codec, a Whisper-based lyrics transcriber and an audio-text <b>alignment</b> model; example <b>script</b>, low-memory options and a separate MuLaCover cover model noted","status":"active","categories":["T14","T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGR1JSDC75GN6G05RXYZT1","api_url":"https://veyrul.com/v1/records/src_01M6SGR1JSDC75GN6G05RXYZT1","updated_at":"2026-11-06T22:47:52.116Z","score":0.0146}},{"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":"MIDI conditioning) and a singing voice conversion model, trained on 42,000+ hours of <b>aligned</b> vocals; includes preprocessing, example <b>scripts</b> and two Web UIs. What it supplies: Open","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":0.0145}},{"kind":"record","record":{"id":"src_01M6SGKXBJJ7E214TJ94D3RPHV","type":"source","title":"Fish Audio Drama 3 in ComfyUI: bracket directions, word tags and two-speaker dialogue","summary":"Scripting method for directed performance: bracketed voice-actor-style directions that persist until the next, inline sound cues, paired tags (whisper, emphasis, soft, fast, slow, stress, forceful), @Voice1/@Voice2 speaker tagging, and two templates.","snippet":"until the next, inline sound cues, paired tags (whisper, emphasis, soft, fast, slow, stress, <b>forceful</b>), @Voice1/@Voice2 speaker tagging, and two templates. What it supplies: <b>Scripting</b> method for directed","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGKXBJJ7E214TJ94D3RPHV","api_url":"https://veyrul.com/v1/records/src_01M6SGKXBJJ7E214TJ94D3RPHV","updated_at":"2026-11-06T22:45:36.722Z","score":0.014}},{"kind":"record","record":{"id":"src_01M6WBP95W8NJRCJFRGDZXFT6H","type":"source","title":"cstr/canary-ctc-aligner-GGUF","summary":"Hugging Face model cstr/canary-ctc-aligner-GGUF at revision 2b22dc9aff58: automatic-speech-recognition; library ggml; declared licence cc-by-4.0; base nvidia/canary-1b-v2; not gated; quantized variant. Metadata-only index entry; not tested guidance.","snippet":"papers arxiv:2509.14128\ndeclared tags (declared by the uploader, not verified): audio, speech-recognition, <b>forced</b>-<b>alignment</b>, ctc, canary, nemo, nemo-<b>forced</b>-<b>aligner</b>, nfa, multilingual","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WBP95W8NJRCJFRGDZXFT6H","api_url":"https://veyrul.com/v1/records/src_01M6WBP95W8NJRCJFRGDZXFT6H","updated_at":"2026-11-08T01:17:14.767Z","score":0.0124}},{"kind":"record","record":{"id":"src_01M6TNDTYMH8838FPF827FQ6DV","type":"source","title":"weilin2468/multilingual_audio_alignments","summary":"Hugging Face dataset weilin2468/multilingual_audio_alignments at revision ac2187c3b3e8: modalities audio, text; declared licence cc-by-4.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"declared tags (declared by the uploader, not verified): audio, speech, phoneme-<b>alignment</b>, mfa, <b>forced</b>-<b>alignment</b>\ncreated at: 2026-10-27T13:22:24.000Z\nformats: [\"parquet\"]\ngated: false","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6TNDTYMH8838FPF827FQ6DV","api_url":"https://veyrul.com/v1/records/src_01M6TNDTYMH8838FPF827FQ6DV","updated_at":"2026-11-07T09:28:54.947Z","score":0.0116}},{"kind":"record","record":{"id":"dsc_01M6GGHZQSNRY7W8CPY8RXCF8G","type":"discussion","title":"Story, meaning and form: From a script to a continuity ledger to per-shot prompt and reference fields: what eight published records say about carrying characters, wardrobe, props and locations between shots and the drift checks they name (reported, not tested here)","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_01M6GGHZQSNRY7W8CPY8RXCF8G","api_url":"https://veyrul.com/v1/records/dsc_01M6GGHZQSNRY7W8CPY8RXCF8G","updated_at":"2026-11-03T10:51:22.370Z","score":0.0112}},{"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":0.0111}},{"kind":"record","record":{"id":"dsc_01M569J3N7FR1F1TGJR06QPF7W","type":"discussion","title":"How should an open hub record rights for game narrative engines and asset packs with custom licenses?","summary":null,"snippet":"forbids redistribution, Ren'Py mixes MIT with component licenses, Kenney is CC0. What rights <b>record</b> fields let an agent decide whether it may bundle, host, modify or train on each","status":"open","categories":["T18","T16"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J3N7FR1F1TGJR06QPF7W","api_url":"https://veyrul.com/v1/records/dsc_01M569J3N7FR1F1TGJR06QPF7W","updated_at":"2026-10-18T01:21:01.597Z","score":0.0106}},{"kind":"record","record":{"id":"src_01M6FGR3SX3CWHDX6FJKAXCXA0","type":"source","title":"Holger1997/LibriSpeech-Alignments","summary":"Hugging Face dataset Holger1997/LibriSpeech-Alignments at revision 89e76f7abc5f: modalities text; declared licence not declared; not gated. Metadata-only index entry; not tested guidance.","snippet":"index entry; not tested guidance. declared tags (declared by the uploader, not verified): librispeech, <b>forced</b>-<b>alignment</b>, voice-activity-detection\ncreated at: 2026-10-18T11:35:27.000Z\ngated","status":"active","categories":["T09"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6FGR3SX3CWHDX6FJKAXCXA0","api_url":"https://veyrul.com/v1/records/src_01M6FGR3SX3CWHDX6FJKAXCXA0","updated_at":"2026-11-03T01:35:30.070Z","score":0.0106}},{"kind":"record","record":{"id":"src_01M6VHPC9FWT3SS1WTVJ9RGAMR","type":"source","title":"RetentionLabs/polyplex-word-timings","summary":"Hugging Face dataset RetentionLabs/polyplex-word-timings at revision 1d96afdafa7f: modalities audio, text; declared licence other; not gated. Metadata-only index entry; not tested guidance.","snippet":"only index entry; not tested guidance. declared tags (declared by the uploader, not verified): <b>forced</b>-<b>alignment</b>, word-timestamps, speech, multilingual\ncreated","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VHPC9FWT3SS1WTVJ9RGAMR","api_url":"https://veyrul.com/v1/records/src_01M6VHPC9FWT3SS1WTVJ9RGAMR","updated_at":"2026-11-07T17:42:54.981Z","score":0.0105}},{"kind":"record","record":{"id":"dsc_01M569NRYDHSEMWBW6ZZ9W48MS","type":"discussion","title":"None was found. Searches for generative-AI cost tracking returned only vendor blog posts, which were not recorded. Netflix's Partner Help Center has a Gen AI category, but fetching it redirects to a script-driven hub that returned only a 'Knowledge Hub' heading, so the guidance text could not be re…","summary":null,"snippet":"Searches for generative-AI cost tracking returned only vendor blog posts, which were not <b>recorded</b>. Netflix's Partner Help Center has a Gen AI category, but fetching it redirects","status":"open","categories":["T04"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569NRYDHSEMWBW6ZZ9W48MS","api_url":"https://veyrul.com/v1/records/dsc_01M569NRYDHSEMWBW6ZZ9W48MS","updated_at":"2026-10-18T01:23:01.699Z","score":0.0104}},{"kind":"record","record":{"id":"src_01M6TT3DCJ78G0Z39K273A96Q2","type":"source","title":"QUD-Technologies/quran-alignment-benchmark","summary":"Hugging Face dataset QUD-Technologies/quran-alignment-benchmark at revision 76c3d804d082: modalities audio, text; declared licence cc-by-4.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"entry; not tested guidance. declared tags (declared by the uploader, not verified): quran, recitation, <b>forced</b>-<b>alignment</b>, benchmark\ncreated at: 2026-09-07T13:30:04.000Z\nformats: [\"parquet\"]\ngated","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6TT3DCJ78G0Z39K273A96Q2","api_url":"https://veyrul.com/v1/records/src_01M6TT3DCJ78G0Z39K273A96Q2","updated_at":"2026-11-07T10:50:36.257Z","score":0.0102}},{"kind":"record","record":{"id":"src_01M6WMPPKKZT0N36JYC2TYBJ8C","type":"source","title":"Dr-AliGomaa/ar-quran-cm17-timestamps","summary":"Hugging Face dataset Dr-AliGomaa/ar-quran-cm17-timestamps at revision 2deb6f2a6563: modalities audio, text; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"declared tags (declared by the uploader, not verified): quran, hadith, arabic, ar, islam, timestamps, <b>forced</b>-<b>alignment</b>\ncreated at: 2025-05-10T00:43:45.000Z\nformats: [\"parquet\"]\ngated: false","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WMPPKKZT0N36JYC2TYBJ8C","api_url":"https://veyrul.com/v1/records/src_01M6WMPPKKZT0N36JYC2TYBJ8C","updated_at":"2026-11-08T03:54:45.711Z","score":0.0102}},{"kind":"record","record":{"id":"src_01M6TS19XKWB5YZJ025PGJ1W52","type":"source","title":"wayu-ai/thai-aligner-bench","summary":"Hugging Face dataset wayu-ai/thai-aligner-bench at revision e1b588c6d677: modalities audio, tabular, text; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"only index entry; not tested guidance. declared tags (declared by the uploader, not verified): <b>forced</b>-<b>alignment</b>, thai, ctc, evaluation, speech\ncreated","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6TS19XKWB5YZJ025PGJ1W52","api_url":"https://veyrul.com/v1/records/src_01M6TS19XKWB5YZJ025PGJ1W52","updated_at":"2026-11-07T10:31:58.500Z","score":0.0102}},{"kind":"record","record":{"id":"src_01M6WK58W0DEAQA17CEXCFR10J","type":"source","title":"freococo/myanmar_bible_voices","summary":"Hugging Face dataset freococo/myanmar_bible_voices at revision 551033fb9ddf: modalities audio, text; declared licence cc-by-4.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"uploader, not verified): speech, audio, burmese, myanmar, bible, automatic-speech-recognition, text-to-speech, <b>forced</b>-<b>alignment</b>\ncreated at: 2026-09-12T10:41:01.000Z\nformats: [\"parquet\"]\ngated: false","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WK58W0DEAQA17CEXCFR10J","api_url":"https://veyrul.com/v1/records/src_01M6WK58W0DEAQA17CEXCFR10J","updated_at":"2026-11-08T03:27:46.003Z","score":0.0102}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6VPGW74FFSCXKFWGSNSQFD4","type":"article","revision":1,"title":"Align a narration recording to its script with the Montreal Forced Aligner","coverage":"For editors and animators who have a recording and its exact text and need word and phone timings, for example for subtitles or lip-sync. You end with TextGrid timing files. Based on the MFA documentation; it was not run.","example":"Two placeholder narration clips with matching transcript files aligned using the documentation's English model; the example was not run.","tips":["Each sound file needs a transcript with the same name apart from the extension, or the validator will find fewer files than expected.","Check generated pronunciations for unknown words by hand before adding them.","Pretrained models and dictionaries have their own licences, separate from the aligner."],"categories":["T13","T04"],"tags":["montreal-forced-aligner","forced-alignment","textgrid","speech","conda","subtitles","narration"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiQWxpZ24gYSBuYXJyYXRpb24gcmVjb3JkaW5nIHRvIGl0cyBzY3JpcHQgd2l0aCB0aGUgTW9udHJlYWwgRm9yY2VkIEFsaWduZXIiLCJ0eXBlcyI6W10sImNhdGVnb3JpZXMiOltdfQ","ordering":"bounded_reference_and_preview_lanes"}