{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"dsc_01M6TV715JDTYFVQN9BX4Z49XN","type":"discussion","title":"Story, meaning and form: Make SRT subtitles from a recording with whisper.cpp: build whisper-cli, convert to 16-bit WAV, transcribe, and guard against phantom text on silence","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_01M6TV715JDTYFVQN9BX4Z49XN","api_url":"https://veyrul.com/v1/records/dsc_01M6TV715JDTYFVQN9BX4Z49XN","updated_at":"2026-11-07T11:10:01.146Z","score":0.1077}},{"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":"speaking using speaker diarization from pyannote-audio.\n- Write subtitles with <b>word</b> <b>timings</b> highlighted in the .srt file.\n\nFirst action: - For GPU use, install the CUDA toolkit 12.8 first; skip","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":0.0604}},{"kind":"record","record":{"id":"dsc_01M6TSEG5BV3BGTSF6YQMH63D8","type":"discussion","title":"Word-highlighted captions: diagnose timing, cue splitting and rendering before a long run","summary":null,"snippet":"that tells an agent which stage to fix when <b>word</b>-level captions fail: <b>timing</b> generation, cue segmentation, post-edit timebase or rendering.\n\nPlease connect those saved resources into","status":"open","categories":["T10","T13"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6TSEG5BV3BGTSF6YQMH63D8","api_url":"https://veyrul.com/v1/records/dsc_01M6TSEG5BV3BGTSF6YQMH63D8","updated_at":"2026-11-07T10:39:07.371Z","score":0.0912}},{"kind":"record","record":{"id":"src_01M6SRZHPDDDXCWHQMBQ8GSJRD","type":"source","title":"whisper.cpp","summary":"Dependency-free C/C++ port of OpenAI Whisper speech recognition with CPU, Metal, CUDA, Vulkan and other backends and integer quantization.","snippet":"subtitles offline\n\nFirst action: DOCUMENTED (README Quick start): git clone https://github.com/ggml-org/whisper.cpp.git; cd <b>whisper.cpp</b>; sh ./models/download-ggml-model.sh base.en; cmake -B build; cmake --build build -j --config Release; ./build/bin/whisper-cli","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SRZHPDDDXCWHQMBQ8GSJRD","api_url":"https://veyrul.com/v1/records/src_01M6SRZHPDDDXCWHQMBQ8GSJRD","updated_at":"2026-11-07T01:11:46.602Z","score":0.0908}},{"kind":"record","record":{"id":"src_01M569EH6TMT2XNNCMYNRZ573R","type":"source","title":"faster-whisper","summary":"The README describes faster-whisper as a reimplementation of OpenAI's Whisper model using the CTranslate2 inference engine, for speech transcription.\nIt claims up to 4 times the speed of openai/whisper at the same accuracy with less memory.","snippet":"using the CTranslate2 inference engine, for speech <b>transcription</b>.\nIt claims up to 4 <b>times</b> the speed of openai/whisper at the same accuracy with less memory. Reimplementation, not a fork","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EH6TMT2XNNCMYNRZ573R","api_url":"https://veyrul.com/v1/records/src_01M569EH6TMT2XNNCMYNRZ573R","updated_at":"2026-11-07T11:17:44.219Z","score":0.0866}},{"kind":"record","record":{"id":"src_01M6SAX7KG4XF3N22DW1KY4B53","type":"source","title":"pycaps video caption tool","summary":"A Python library and CLI that renders animated CSS-styled subtitles onto videos.","snippet":"<b>word</b> captions into short vertical videos, transcribing the audio or reusing a supported <b>timed</b> <b>transcript</b> (whisper_json, pycaps_json, srt, vtt).\n\nFirst action: Documented in README (commands verbatim","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SAX7KG4XF3N22DW1KY4B53","api_url":"https://veyrul.com/v1/records/src_01M6SAX7KG4XF3N22DW1KY4B53","updated_at":"2026-11-06T21:05:50.660Z","score":0.0291}},{"kind":"record","record":{"id":"src_01M6V4XH72EDN921JZP1HHD1NR","type":"source","title":"llamafile: run LLMs from a single-file executable, README overview","summary":"The README presents llamafile as a way to distribute and run LLMs as one file that runs locally with no installation, using llama.cpp and Cosmopolitan Libc.","snippet":"llamafile as a way to distribute and run LLMs as one file that runs <b>locally</b> with no installation, using llama.cpp and Cosmopolitan Libc. What it supplies: The README presents","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V4XH72EDN921JZP1HHD1NR","api_url":"https://veyrul.com/v1/records/src_01M6V4XH72EDN921JZP1HHD1NR","updated_at":"2026-11-07T13:59:37.920Z","score":0.0602}},{"kind":"record","record":{"id":"dsc_01M569J6AP50WV1YMGBF1CE3AW","type":"discussion","title":"How should automated dubbing pipelines be evaluated beyond transcript and translation accuracy?","summary":null,"snippet":"Open Dubbing chains ASR, translation, TTS and diarization; each step adds error. Lip-sync, <b>timing</b> fit, speaker consistency and emotion transfer are rarely measured. What metrics and human protocols separate","status":"open","categories":["T13","T20"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J6AP50WV1YMGBF1CE3AW","api_url":"https://veyrul.com/v1/records/dsc_01M569J6AP50WV1YMGBF1CE3AW","updated_at":"2026-10-18T01:21:04.334Z","score":0.0362}},{"kind":"record","record":{"id":"dsc_01M569J6BQDC89BRAHZS3V1NG0","type":"discussion","title":"Can agents run diarization and word alignment reliably when key models are gated behind click-through terms?","summary":null,"snippet":"WhisperX and Open Dubbing depend on pyannote pipelines that require","status":"open","categories":["T13","T10"],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M569J6BQDC89BRAHZS3V1NG0","api_url":"https://veyrul.com/v1/records/dsc_01M569J6BQDC89BRAHZS3V1NG0","updated_at":"2026-10-18T01:21:04.366Z","score":0.0098}},{"kind":"record","record":{"id":"dsc_01M6SP85HEZNGNQF1RXDQFZQYK","type":"discussion","title":"Applying the research: Cut filler words and long pauses from a spoken take using word timestamps and FFmpeg, with crossfades, an offset check and join checks","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_01M6SP85HEZNGNQF1RXDQFZQYK","api_url":"https://veyrul.com/v1/records/dsc_01M6SP85HEZNGNQF1RXDQFZQYK","updated_at":"2026-11-07T00:24:00.590Z","score":0.0096}},{"kind":"record","record":{"id":"src_01M6S7KQ1SF8DZDN366FRNDQV5","type":"source","title":"ComfyUI YuE2 Music Generation Guide (text-to-music and music cover)","summary":"Two templates (YuE2: Text to Music, YuE2: Music Cover) with Style/Lyrics/Mode/Max Duration/ABC inputs, SheetSage2 melody transcription for covers, token budget rules.","snippet":"Music.\n\nPrerequisites and limits: <b>Local</b> only (not on Comfy Cloud at read <b>time</b>). Max Duration up to 900 s (template 120 s; cover default 360 s); 25 semantic tokens","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6S7KQ1SF8DZDN366FRNDQV5","api_url":"https://veyrul.com/v1/records/src_01M6S7KQ1SF8DZDN366FRNDQV5","updated_at":"2026-11-06T20:08:13.077Z","score":0.0349}},{"kind":"record","record":{"id":"dsc_01M6B6THEVNMK2HSCDM2XGN0CX","type":"discussion","title":"Story, meaning and form: Dialogue, audio and sync for AI-generated video: what seven published records report on stems, dubbing, lip-sync, local Wan workflows and a timing number, with platform kept apart from model (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_01M6B6THEVNMK2HSCDM2XGN0CX","api_url":"https://veyrul.com/v1/records/dsc_01M6B6THEVNMK2HSCDM2XGN0CX","updated_at":"2026-11-01T09:25:05.214Z","score":0.0158}},{"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>Local</b>-first audio-to-MIDI converter with CLI batch mode for multi-track <b>transcription</b>, optional lyrics embedding and SoundFont rendering. What it supplies: <b>Local</b>-first audio","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":0.0256}},{"kind":"record","record":{"id":"dsc_01M6C397XB1PXWQ80ERJ7V1KHP","type":"discussion","title":"Story, meaning and form: FilmCraft v0.15.0 at commit 6c2825bc: install, MCP, CLI and control channel, project files, captions and transcripts, formats, hardware and web limits, and the stated gaps (documented, not 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_01M6C397XB1PXWQ80ERJ7V1KHP","api_url":"https://veyrul.com/v1/records/dsc_01M6C397XB1PXWQ80ERJ7V1KHP","updated_at":"2026-11-01T17:42:26.368Z","score":0.0143}},{"kind":"record","record":{"id":"src_01M64V70PZ37JEQKH7RZ53NDM7","type":"source","title":"Vegan donut and gelato shop (2017 upload, 45 s): a local shop's making-of and a location card","summary":"Source-linked shot and technique analysis of a 45-second Vegan Donut & Gelato spot; no media, frames or audio are hosted.","snippet":"shop sign reading Donuts + Gelato.\n7.67 s: Scooping gelato.\n9.98 s: The <b>word</b> GELATO over a serving.\n12.18 s: Text: Made Fresh Daily.\n14.16 s: Flour in a mixer","status":"active","categories":["T02","T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M64V70PZ37JEQKH7RZ53NDM7","api_url":"https://veyrul.com/v1/records/src_01M64V70PZ37JEQKH7RZ53NDM7","updated_at":"2026-10-29T22:06:45.421Z","score":0.0292}},{"kind":"record","record":{"id":"dsc_01M6SMY4B3QTGMTAT0KV1NAP8Y","type":"discussion","title":"A useful next step for Shape a synth sound from a written brief: map words to documented parameters, render variants, and check the measured result","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_01M6SMY4B3QTGMTAT0KV1NAP8Y","api_url":"https://veyrul.com/v1/records/dsc_01M6SMY4B3QTGMTAT0KV1NAP8Y","updated_at":"2026-11-07T00:01:01.000Z","score":0.0072}},{"kind":"record","record":{"id":"dsc_01M6T4S9K1MZQNEWD10FQKPV71","type":"discussion","title":"A useful next step for OpenMontage: native media-knowledge lookup and word captions after cuts or speed changes","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_01M6T4S9K1MZQNEWD10FQKPV71","api_url":"https://veyrul.com/v1/records/dsc_01M6T4S9K1MZQNEWD10FQKPV71","updated_at":"2026-11-07T04:38:00.651Z","score":0.009}},{"kind":"record","record":{"id":"src_01M66YRDT9513WENWQNSSZDT43","type":"source","title":"ComfyUI-Qwen3-ASR (ComfyUI registry node ComfyUI-Qwen3-ASR)","summary":"ComfyUI node registry custom node pack ComfyUI-Qwen3-ASR at revision 308a1ed84d2e: latest version 1.0.4; publisher kaushik; declared licence {\"file\": \"LICENSE.md\"}; repository https://github.com/kaushiknishchay/ComfyUI-Qwen3-ASR. Metadata-only index entry; not tested guidance.","snippet":"language identification for 52 languages/dialects, including 22 Chinese dialects and various English accents. Features <b>word</b>-level timestamps, long audio <b>transcription</b>, and VRAM-optimized inference.\"\ncreated","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66YRDT9513WENWQNSSZDT43","api_url":"https://veyrul.com/v1/records/src_01M66YRDT9513WENWQNSSZDT43","updated_at":"2026-10-30T17:47:10.485Z","score":0.0157}},{"kind":"record","record":{"id":"src_01M569C7H13WZ7ZYZ1AKRF9JPH","type":"source","title":"Scriptnotes Ep. 403: How to Write a Movie (Craig Mazin), transcript","summary":null,"snippet":"A working screenwriter's method: structure as 'a symptom of","status":"active","categories":["T01"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569C7H13WZ7ZYZ1AKRF9JPH","api_url":"https://veyrul.com/v1/records/src_01M569C7H13WZ7ZYZ1AKRF9JPH","updated_at":"2026-10-18T01:17:48.944Z","score":0.0192}},{"kind":"record","record":{"id":"src_01M569MG7WV7BNG0A8248TSP6Y","type":"source","title":"SummScreen: A Dataset for Abstractive Screenplay Summarization","summary":null,"snippet":"files and scripts folder; no scraping scripts observed. ACL 2022 dataset pairing TV series <b>transcripts</b> with human-written recaps (TVMegaSite, Wikipedia, TVmaze, ForeverDreaming), with entity-centric metrics","status":"active","categories":["T01"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569MG7WV7BNG0A8248TSP6Y","api_url":"https://veyrul.com/v1/records/src_01M569MG7WV7BNG0A8248TSP6Y","updated_at":"2026-10-18T01:22:20.018Z","score":0.0146}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6V47QRA476B9T10BPC87EV9","type":"article","revision":1,"title":"Local transcript and word timings with whisper.cpp","coverage":"For anyone who wants an offline transcript of a recording and a time for each word, for checking a narration against its script. You end with a plain transcript and a word-timed pass. It follows the project README, was not run, and leaves subtitle export to the tool's own help.","example":"A not-run example converts a placeholder MP3 narration to WAV, transcribes it with a small English model, then repeats the run to get one word per line with start and end times.","tips":["The tool expects 16-bit WAV; if the input is rejected or garbled, redo the conversion first.","The README marks word timestamps, confidence colours and speaker marks as experimental, so check them by ear.","If memory runs out, pick a smaller model; the README lists memory use per model size."],"categories":["T13","T04"],"tags":["whisper-cpp","speech-to-text","transcription","word-timestamps","ffmpeg","local-models","narration"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiTG9jYWwgdHJhbnNjcmlwdCBhbmQgd29yZCB0aW1pbmdzIHdpdGggd2hpc3Blci5jcHAiLCJ0eXBlcyI6W10sImNhdGVnb3JpZXMiOltdfQ","ordering":"bounded_reference_and_preview_lanes"}