{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"src_01M6V5KVEB336053WGZ1R7RW55","type":"source","title":"Vosk: offline speech recognition toolkit, README overview","summary":"The README presents Vosk as an offline open source speech recognition toolkit for 20+ languages and dialects.","snippet":"README presents Vosk as an <b>offline</b> open source speech recognition toolkit for 20+ languages and dialects. What it supplies: The README presents Vosk as an <b>offline</b> open source speech recognition","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V5KVEB336053WGZ1R7RW55","api_url":"https://veyrul.com/v1/records/src_01M6V5KVEB336053WGZ1R7RW55","updated_at":"2026-11-07T14:11:49.291Z","score":0.086}},{"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":"Useful for: - Transcribe speech with word-level timestamps aligned using wav2vec2.\n- Label who is <b>speaking</b> using speaker diarization from pyannote-audio.\n- Write subtitles with word timings highlighted","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":0.0418}},{"kind":"record","record":{"id":"src_01M6WG8T7MGSS1NGAK639F9QZW","type":"source","title":"SPEAK-ASR/openslr-sinhala-asr","summary":"Hugging Face dataset SPEAK-ASR/openslr-sinhala-asr at revision c4fe10a312b6: modalities audio, text; declared licence not declared; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face dataset <b>SPEAK</b>-ASR/openslr-sinhala-asr at revision c4fe10a312b6: modalities audio, <b>text</b>; declared licence not declared; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WG8T7MGSS1NGAK639F9QZW","api_url":"https://veyrul.com/v1/records/src_01M6WG8T7MGSS1NGAK639F9QZW","updated_at":"2026-11-08T02:37:16.330Z","score":0.0413}},{"kind":"record","record":{"id":"src_01M6WK5EHV8487Q6J1KM22ZQPX","type":"source","title":"SPEAK-ASR/openslr-sinhala-asr-norm","summary":"Hugging Face dataset SPEAK-ASR/openslr-sinhala-asr-norm at revision 4448fac37eb9: modalities audio, text; declared licence not declared; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face dataset <b>SPEAK</b>-ASR/openslr-sinhala-asr-norm at revision 4448fac37eb9: modalities audio, <b>text</b>; declared licence not declared; not gated. Metadata-only index entry; not tested guidance. created","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WK5EHV8487Q6J1KM22ZQPX","api_url":"https://veyrul.com/v1/records/src_01M6WK5EHV8487Q6J1KM22ZQPX","updated_at":"2026-11-08T03:27:51.816Z","score":0.0411}},{"kind":"record","record":{"id":"src_01M6V4XND49NYJGKXMNQPYHVRB","type":"source","title":"Open WebUI: self-hosted AI platform, README install and licence notes","summary":"The README presents Open WebUI as a self-hosted platform built to run entirely offline, connecting local models through Ollama or OpenAI-compatible APIs.","snippet":"README presents Open WebUI as a self-hosted platform built to run entirely <b>offline</b>, connecting local models through Ollama or OpenAI-compatible APIs. What it supplies: The README presents Open","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V4XND49NYJGKXMNQPYHVRB","api_url":"https://veyrul.com/v1/records/src_01M6V4XND49NYJGKXMNQPYHVRB","updated_at":"2026-11-07T13:59:42.207Z","score":0.0387}},{"kind":"record","record":{"id":"src_01M66HRRGH7VZ5PB13XE92X1YX","type":"source","title":"ComfyUI FunASR - Offline Chinese Speech to Text (ComfyUI registry node ComfyUI-FunASR)","summary":"ComfyUI node registry custom node pack ComfyUI-FunASR at revision 4daf67974dff: latest version 1.0.0; publisher ahkimkoo; declared licence {\"text\": \"MIT\"}; repository https://github.com/ahkimkoo/ComfyUI-FunASR. Metadata-only index entry; not tested guidance.","snippet":"upstream description (quoted from the ComfyUI registry listing, not verified): \"ComfyUI custom node for <b>offline</b> Chinese speech-to-<b>text</b> using FunASR with VAD and punctuation support.\"\ncreated","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66HRRGH7VZ5PB13XE92X1YX","api_url":"https://veyrul.com/v1/records/src_01M66HRRGH7VZ5PB13XE92X1YX","updated_at":"2026-10-30T14:00:09.952Z","score":0.0361}},{"kind":"record","record":{"id":"src_01M6V8ETC68RASAA4MDB69DDMQ","type":"source","title":"FunASR: speech recognition toolkit for offline, streaming and edge use, README overview","summary":"The README presents FunASR as a speech recognition toolkit for offline, streaming and edge use, with models for ASR, VAD, punctuation, speaker work and more.","snippet":"README presents FunASR as a speech recognition toolkit for <b>offline</b>, streaming and edge use, with models for ASR, VAD, punctuation, speaker work and more. What it supplies: The README presents","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V8ETC68RASAA4MDB69DDMQ","api_url":"https://veyrul.com/v1/records/src_01M6V8ETC68RASAA4MDB69DDMQ","updated_at":"2026-11-07T15:01:30.080Z","score":0.0336}},{"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":"Basic Pitch is a <b>Python</b> library for automatic music transcription. It uses a lightweight neural network from Spotify's Audio Intelligence Lab to turn audio into MIDI.\nIt generates","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":0.0326}},{"kind":"record","record":{"id":"src_01M569CR1572T5NEQ2ZRJAEW1F","type":"source","title":"huggingface/peft","summary":"The README presents PEFT as a library of parameter-efficient fine-tuning methods that adapt large pretrained models at much lower cost.","snippet":"tune a large model with LoRA by training only a small share of parameters.\n- <b>Save</b> and reload small adapters instead of full models.\n- Use it with Transformers, Diffusers","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CR1572T5NEQ2ZRJAEW1F","api_url":"https://veyrul.com/v1/records/src_01M569CR1572T5NEQ2ZRJAEW1F","updated_at":"2026-11-07T15:31:26.245Z","score":0.0334}},{"kind":"record","record":{"id":"src_01M6WCN5FCNYVP4W1A69D109W5","type":"source","title":"Show-1: text-to-video generation combining pixel and latent diffusion","summary":"Show-1 is a text-to-video generation method from Show Lab (accepted at IJCV), released with code and weights in October 2023. The README lists separate models on Hugging Face for the base, interpolation and two super-resolution stages, with the first super-resolution model using DeepFloyd-IF to upsample the first frame. Running python run_inference.py generates a video from a text prompt and saves the output of each stage as GIFs in an outputs folder, fetching weights from Hugging Face automatically.","snippet":"Show-1 is a <b>text</b>-to-video generation method from Show Lab (accepted at IJCV), released with code and weights in October 2023. The README lists separate models","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WCN5FCNYVP4W1A69D109W5","api_url":"https://veyrul.com/v1/records/src_01M6WCN5FCNYVP4W1A69D109W5","updated_at":"2026-11-08T01:34:06.788Z","score":0.026}},{"kind":"record","record":{"id":"src_01M6TVN0NMTK1J8FW8GKGX426N","type":"source","title":"Kokoro: open-weight 82M text-to-speech inference library, README overview","summary":"The README describes Kokoro as an open-weight text-to-speech model with 82 million parameters, offered through an inference library, with Apache-licensed weights.","snippet":"README describes Kokoro as an open-weight <b>text</b>-to-speech model with 82 million parameters, offered through an inference library, with Apache-licensed weights. What it supplies: The README","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6TVN0NMTK1J8FW8GKGX426N","api_url":"https://veyrul.com/v1/records/src_01M6TVN0NMTK1J8FW8GKGX426N","updated_at":"2026-11-07T11:17:41.648Z","score":0.0149}},{"kind":"record","record":{"id":"src_01M569CQPGFD84W0XCFANB6CZ7","type":"source","title":"bitsandbytes-foundation/bitsandbytes","summary":"The README presents bitsandbytes as quantization building blocks that cut memory for LLM inference and training.","snippet":"with LLM.int8().\n- Fine-tune with QLoRA 4-bit training.\n- Use 8-bit optimizers to <b>save</b> training memory.\n\nFirst action: - Install it for your accelerator following the project documentation","status":"active","categories":["T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CQPGFD84W0XCFANB6CZ7","api_url":"https://veyrul.com/v1/records/src_01M569CQPGFD84W0XCFANB6CZ7","updated_at":"2026-11-07T16:19:17.977Z","score":0.0325}},{"kind":"record","record":{"id":"src_01M6SGG6SK5QBB7S9FK7NYRC0V","type":"source","title":"Stable Audio 1.0 text-to-audio workflow in ComfyUI","summary":"Core-node text-to-audio graph: CheckpointLoaderSimple, CLIPTextEncode, EmptyLatentAudio (default 47.6 s), KSampler, VAE decode, save to output/audio.","snippet":"Core-node <b>text</b>-to-audio graph: CheckpointLoaderSimple, CLIPTextEncode, EmptyLatentAudio (default 47.6 s), KSampler, VAE decode, <b>save</b> to output/audio. What it supplies: Core-node <b>text</b>-to-audio graph","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGG6SK5QBB7S9FK7NYRC0V","api_url":"https://veyrul.com/v1/records/src_01M6SGG6SK5QBB7S9FK7NYRC0V","updated_at":"2026-11-06T22:43:35.312Z","score":0.0064}},{"kind":"record","record":{"id":"src_01M6W7JQN6YBR90Q2NHV0A2GV1","type":"source","title":"eSpeak NG: compact open source text-to-speech synthesizer, README overview","summary":"The README presents eSpeak NG as a small, fast, multilingual formant text-to-speech engine.","snippet":"README presents eSpeak NG as a small, fast, multilingual formant <b>text</b>-to-speech engine. What it supplies: The README presents eSpeak NG as a small, fast, multilingual formant <b>text</b>","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6W7JQN6YBR90Q2NHV0A2GV1","api_url":"https://veyrul.com/v1/records/src_01M6W7JQN6YBR90Q2NHV0A2GV1","updated_at":"2026-11-08T00:05:24.223Z","score":0.0072}},{"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":"Useful for: spoken audio: transcribe interviews, podcasts or voiceover to <b>text</b> and subtitles <b>offline</b>\n\nFirst action: DOCUMENTED (README Quick start): git clone https://github.com/ggml-org/whisper.cpp.git; cd whisper.cpp; sh ./models/download-ggml-model.sh","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":0.0234}},{"kind":"record","record":{"id":"src_01M670ZMR91W6T4SK7YX4X17FH","type":"source","title":"ComfyUI Save TIFF (ComfyUI registry node ComfyUI-Save-TIFF)","summary":"ComfyUI node registry custom node pack ComfyUI-Save-TIFF at revision 0c022478145b: latest version 1.0.0; publisher driftjohnson; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/MushroomFleet/comfyui-save-tiff. Metadata-only index entry; not tested guidance.","snippet":"ComfyUI node registry custom node pack ComfyUI-<b>Save</b>-TIFF at revision 0c022478145b: latest version 1.0.0; publisher driftjohnson; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/MushroomFleet/comfyui-save-tiff. Metadata-only index entry","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M670ZMR91W6T4SK7YX4X17FH","api_url":"https://veyrul.com/v1/records/src_01M670ZMR91W6T4SK7YX4X17FH","updated_at":"2026-10-30T18:26:04.124Z","score":0.0188}},{"kind":"record","record":{"id":"src_01M670ZNCKM81SVVYXFA6SWQXX","type":"source","title":"Save Uncompressed 16 Bit PNG (ComfyUI registry node ComfyUI-Save16bitPng)","summary":"ComfyUI node registry custom node pack ComfyUI-Save16bitPng at revision 4c3da1225f10: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/yolanother/ComfyUI-Save16bitPng. Metadata-only index entry; not tested guidance.","snippet":"quoted from the ComfyUI registry listing, not verified): \"The SaveImageARGB16PNG node provides functionality for <b>saving</b> images as uncompressed PNG files with ARGB16 precision. This node is particularly useful","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M670ZNCKM81SVVYXFA6SWQXX","api_url":"https://veyrul.com/v1/records/src_01M670ZNCKM81SVVYXFA6SWQXX","updated_at":"2026-10-30T18:26:04.778Z","score":0.0164}},{"kind":"record","record":{"id":"src_01M6V7Q54BDKTC6DBE3H4FNJSG","type":"source","title":"HunyuanVideo: large text-to-video generation model with inference code","summary":"This repository contains PyTorch model definitions, pre-trained weights and inference and sampling code for HunyuanVideo, a large video generation model. The README's news lists later releases (HunyuanVideo-I2V for image-to-video, HunyuanCustom, HunyuanVideo-Avatar and HunyuanVideo-1.5), FP8 weights, parallel inference with xDiT and Diffusers integration.","snippet":"parallel inference with xDiT and Diffusers integration.\n\nUseful for: - Generate a 540p or 720p <b>text</b>-to-video clip of 129 frames with sample_video.py and a <b>text</b> prompt","status":"active","categories":["T06"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6V7Q54BDKTC6DBE3H4FNJSG","api_url":"https://veyrul.com/v1/records/src_01M6V7Q54BDKTC6DBE3H4FNJSG","updated_at":"2026-11-07T14:48:34.666Z","score":0.013}},{"kind":"record","record":{"id":"src_01M670Z66Z8EKS3FPN2NQVSPM5","type":"source","title":"Save Image With Callback (ComfyUI registry node ComfyUI-Save-Image-Callback)","summary":"ComfyUI node registry custom node pack ComfyUI-Save-Image-Callback at revision ce6245bc03dc: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/WUYUDING2583/ComfyUI-Save-Image-Callback. Metadata-only index entry; not tested guidance.","snippet":"ComfyUI node registry custom node pack ComfyUI-<b>Save</b>-Image-Callback at revision ce6245bc03dc: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/WUYUDING2583/ComfyUI-Save-Image-Callback. Metadata-only index","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M670Z66Z8EKS3FPN2NQVSPM5","api_url":"https://veyrul.com/v1/records/src_01M670Z66Z8EKS3FPN2NQVSPM5","updated_at":"2026-10-30T18:25:49.237Z","score":0.0185}},{"kind":"record","record":{"id":"src_01M66YT6ZW7YDH60HSSZWEMN6S","type":"source","title":"ComfyUI Load and Save file to S3 (ComfyUI registry node ComfyUI-S3-Tools)","summary":"ComfyUI node registry custom node pack ComfyUI-S3-Tools at revision 57ccfe8f7b5c: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/kealiu/ComfyUI-S3-Tools. Metadata-only index entry; not tested guidance.","snippet":"upstream description (quoted from the ComfyUI registry listing, not verified): \"Nodes:Load From S3, <b>Save</b> To S3.\"\ncreated at: 2025-03-11T23:57:58.71683Z\nlicense: {}\nname: ComfyUI","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66YT6ZW7YDH60HSSZWEMN6S","api_url":"https://veyrul.com/v1/records/src_01M66YT6ZW7YDH60HSSZWEMN6S","updated_at":"2026-10-30T17:48:09.045Z","score":0.0166}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6W5V6BP0PSVKBNE7GZHV035","type":"article","revision":1,"title":"Speak and save text offline in Python with pyttsx3","coverage":"For writers and editors who want to hear a scene read aloud or make a scratch voice track without a cloud service. You end with a short Python script that speaks a line and saves it to a file using the voices already on your computer. Based on the README; it was not run.","example":"A not-run example speaks one line from a story chapter at a set rate, lists the installed voices and saves the same line to a WAV file.","tips":["No sound on Linux usually means espeak-ng and libespeak1 are missing.","The README does not list which audio formats each engine can write, so if a saved file will not play, try another extension or engine.","Voices come from your operating system and have their own terms, separate from the library's MPL 2.0 licence."],"categories":["T13","T04"],"tags":["pyttsx3","text-to-speech","offline","python","scratch-audio","mpl-2","espeak"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiU3BlYWsgYW5kIHNhdmUgdGV4dCBvZmZsaW5lIGluIFB5dGhvbiB3aXRoIHB5dHRzeDMiLCJ0eXBlcyI6W10sImNhdGVnb3JpZXMiOltdfQ","ordering":"bounded_reference_and_preview_lanes"}