{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"dsc_01M6V9BATGDAQF8NFQ2H7FWHYY","type":"discussion","title":"Creative practice with Generate short narration clips with Bark: install from the Suno repo, pick a voice preset, add sound cues and write WAV files","summary":null,"snippet":"Turn <b>one</b> supported capability into a bounded creative experiment. State the intention, choose a contrasting alternative and inspect actual outputs if generated. Preserve technical observations separately from taste. Produce","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6V9BATGDAQF8NFQ2H7FWHYY","api_url":"https://veyrul.com/v1/records/dsc_01M6V9BATGDAQF8NFQ2H7FWHYY","updated_at":"2026-11-07T15:17:00.684Z","score":0.7213}},{"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":0.6257}},{"kind":"record","record":{"id":"src_01M6SB1XKGZD7Y34X6J8VQCS7E","type":"source","title":"kokoro-tts CLI","summary":"Command-line Kokoro TTS tool with voice blending and EPUB/PDF input.","snippet":"<b>TTS</b> tool with voice blending and EPUB/PDF input.\n\nUseful for: spoken audio/publishing: <b>narrate</b> books from the terminal\n\nFirst action: DOCUMENTED (README): install with uv tool install <b>kokoro</b>","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SB1XKGZD7Y34X6J8VQCS7E","api_url":"https://veyrul.com/v1/records/src_01M6SB1XKGZD7Y34X6J8VQCS7E","updated_at":"2026-11-06T21:08:24.271Z","score":0.5633}},{"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":0.4571}},{"kind":"record","record":{"id":"src_01M67EFV56R3EYMNBMX2B5CZ7W","type":"source","title":"ComfyUI-kokoro-TTS (ComfyUI registry node ComfyUI-kokoro-TTS)","summary":"ComfyUI node registry custom node pack ComfyUI-kokoro-TTS at revision 30add98f9673: latest version 1.0.0; publisher apacheone; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/Apache0ne/ComfyUI-kokoro. Metadata-only index entry; not tested guidance.","snippet":"ComfyUI node registry custom node pack ComfyUI-<b>kokoro</b>-<b>TTS</b> at revision 30add98f9673: latest version 1.0.0; publisher apacheone; declared licence {\"<b>file</b>\": \"LICENSE\"}; repository https://github.com/Apache0ne/ComfyUI-kokoro. Metadata-only","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M67EFV56R3EYMNBMX2B5CZ7W","api_url":"https://veyrul.com/v1/records/src_01M67EFV56R3EYMNBMX2B5CZ7W","updated_at":"2026-10-30T22:22:06.462Z","score":0.2451}},{"kind":"record","record":{"id":"src_01M66HS7FS1AMCRTAC49ZFZT2N","type":"source","title":"ComfyUI-Geeky-Kokoro-TTS (ComfyUI registry node ComfyUI-Geeky-Kokoro-TTS)","summary":"ComfyUI node registry custom node pack ComfyUI-Geeky-Kokoro-TTS at revision 8d7602334c59: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/GeekyGhost/ComfyUI-Geeky-Kokoro-TTS. Metadata-only index entry; not tested guidance.","snippet":"ComfyUI node registry custom node pack ComfyUI-Geeky-<b>Kokoro</b>-<b>TTS</b> at revision 8d7602334c59: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/GeekyGhost/ComfyUI-Geeky-Kokoro-TTS. Metadata-only","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66HS7FS1AMCRTAC49ZFZT2N","api_url":"https://veyrul.com/v1/records/src_01M66HS7FS1AMCRTAC49ZFZT2N","updated_at":"2026-10-30T14:00:25.300Z","score":0.2442}},{"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":"README presents Bark as a generative <b>text</b>-to-audio model for speech, music and sound, not a conventional <b>TTS</b> system. What it supplies: The README 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":0.2198}},{"kind":"record","record":{"id":"src_01M569EGMX9DQ3VM1WBZH8A22G","type":"source","title":"Piper TTS (OHF-Voice piper1-gpl)","summary":"The README describes Piper as a fast and local neural text-to-speech engine that embeds espeak-ng for phonemization.\nIt is labelled as a library from the Open Home Foundation.","snippet":"README describes Piper as a fast and <b>local</b> neural <b>text</b>-to-speech engine that embeds espeak-ng for phonemization.\nIt is labelled as a library from the Open Home","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EGMX9DQ3VM1WBZH8A22G","api_url":"https://veyrul.com/v1/records/src_01M569EGMX9DQ3VM1WBZH8A22G","updated_at":"2026-11-07T11:11:25.142Z","score":0.2195}},{"kind":"record","record":{"id":"src_01M6SK9EXPX9WMTZZPH0ACQ83M","type":"source","title":"HeyGen Voice 1.0 in ComfyUI: instant voice clone and text to speech","summary":"Instant Clone node (voice_id from one-speaker clip, similarity levels) feeding a TTS node (heygen-voice-1 or turbo, expressiveness_boost) with documented limits.","snippet":"boost) with documented limits.\n\nUseful for: Voiceover makers wanting a reusable cloned voice for <b>narration</b> up to about 12 minutes <b>per</b> call.\n\nFirst action: Open 'HeyGen Voice 1.0' template","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SK9EXPX9WMTZZPH0ACQ83M","api_url":"https://veyrul.com/v1/records/src_01M6SK9EXPX9WMTZZPH0ACQ83M","updated_at":"2026-11-06T23:32:19.990Z","score":0.2189}},{"kind":"record","record":{"id":"src_01M569EGDW6WNG855N2P50A2AN","type":"source","title":"Kokoro-82M","summary":"Hugging Face model hexgrad/Kokoro-82M at revision f3ff3571791e: text-to-speech; declared licence apache-2.0; base yl4579/StyleTTS2-LJSpeech; not gated; finetune variant. Metadata-only index entry; not tested guidance.","snippet":"Apache-2.0, trained <b>per</b> the card on permissive/non-copyrighted audio; light enough for CPU/edge <b>narration</b> and scratch dialogue","status":"active","categories":["T13","T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569EGDW6WNG855N2P50A2AN","api_url":"https://veyrul.com/v1/records/src_01M569EGDW6WNG855N2P50A2AN","updated_at":"2026-10-30T07:59:55.332Z","score":0.2174}},{"kind":"record","record":{"id":"src_01M6S6W9MAPP8Y9T04S82VPRKD","type":"source","title":"Voice-Pro","summary":"Gradio web UI combining YouTube download, voice separation, speech recognition, translation, TTS and dubbing.","snippet":"Gradio web UI combining YouTube download, voice separation, speech recognition, translation, <b>TTS</b> and dubbing. What it supplies: Gradio web UI combining YouTube download, voice separation, speech recognition, translation, <b>TTS</b>","status":"active","categories":["T13"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6S6W9MAPP8Y9T04S82VPRKD","api_url":"https://veyrul.com/v1/records/src_01M6S6W9MAPP8Y9T04S82VPRKD","updated_at":"2026-11-06T19:55:25.669Z","score":0.2171}},{"kind":"record","record":{"id":"src_01M6SK9849NDV7FS1GFTFC73B0","type":"source","title":"ElevenLabs partner nodes in ComfyUI: TTS, speech-to-speech, Scribe v2, sound effects, dialogue, voice isolation","summary":"Overview of six cloud audio capabilities (Eleven v3, Multilingual v2, Flash v2.5 TTS; speech-to-speech; Scribe v2 transcription with up to 32-speaker diarization; text-to-SFX; text-to-dialogue; voice isolation) with sub-pages per node.","snippet":"Overview of six cloud audio capabilities (Eleven v3, Multilingual v2, Flash v2.5 <b>TTS</b>; speech-to-speech; Scribe v2 transcription with up to 32-speaker diarization; <b>text</b>","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SK9849NDV7FS1GFTFC73B0","api_url":"https://veyrul.com/v1/records/src_01M6SK9849NDV7FS1GFTFC73B0","updated_at":"2026-11-06T23:32:13.031Z","score":0.2092}},{"kind":"record","record":{"id":"src_01M569MKN0EXEMDFMX4J0DZG5T","type":"source","title":"Style-Bert-VITS2 (litagin02): Bert-VITS2 with controllable voice styles, Japanese TTS and training UI","summary":null,"snippet":"their own terms (JVNV corpus CC BY-SA 4.0; あみたろ/小春音アミ with credit requirement) <b>per</b> docs/TERMS_OF_USE.md. Japanese-first expressive <b>TTS</b> built on Bert-VITS2 v2.1 and JP-Extra","status":"active","categories":["T13","T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569MKN0EXEMDFMX4J0DZG5T","api_url":"https://veyrul.com/v1/records/src_01M569MKN0EXEMDFMX4J0DZG5T","updated_at":"2026-10-18T01:22:23.509Z","score":0.2079}},{"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":"ByteDanceSeedAudio node with four modes (<b>text</b> only, up to three @Audio references, <b>one</b> character image, preset <b>TTS</b> 2.0 voice) and three templates; speech rate, pitch, loudness","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":0.2078}},{"kind":"record","record":{"id":"src_01M6WM3TQXZS2AZYJGA38E2RXF","type":"source","title":"ghananlpcommunity/poto-tts-kokoro-gh","summary":"Hugging Face model ghananlpcommunity/poto-tts-kokoro-gh at revision ffc9a3ace6ab: text-to-speech; library poto-tts; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model ghananlpcommunity/poto-tts-kokoro-gh at revision ffc9a3ace6ab: <b>text</b>-to-speech; library poto-<b>tts</b>; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance. declared tags","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WM3TQXZS2AZYJGA38E2RXF","api_url":"https://veyrul.com/v1/records/src_01M6WM3TQXZS2AZYJGA38E2RXF","updated_at":"2026-11-08T03:44:27.324Z","score":0.2077}},{"kind":"record","record":{"id":"src_01M6W1D35PTJSNHE7VR8F0T6Y8","type":"source","title":"soniqo/Kokoro-82M-German-Victoria-ONNX","summary":"Hugging Face model soniqo/Kokoro-82M-German-Victoria-ONNX at revision 6f9913452e55: text-to-speech; library onnxruntime; declared licence apache-2.0; base kikiri-tts/kikiri-german-victoria; not gated; quantized variant. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model soniqo/Kokoro-82M-German-Victoria-ONNX at revision 6f9913452e55: <b>text</b>-to-speech; library onnxruntime; declared licence apache-2.0; base kikiri-<b>tts</b>/kikiri-german-victoria; not gated; quantized variant. Metadata-only index entry","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6W1D35PTJSNHE7VR8F0T6Y8","api_url":"https://veyrul.com/v1/records/src_01M6W1D35PTJSNHE7VR8F0T6Y8","updated_at":"2026-11-07T22:17:27.947Z","score":0.2076}},{"kind":"record","record":{"id":"src_01M6S7KSHXWMZZHCTPETPSMXWV","type":"source","title":"Fish Audio Prompt Guide: writing tags for Fish Audio TTS in ComfyUI (s2.1-pro and s1)","summary":"Prompting rules: position-is-meaning bracket cues, about 50 emotions, tone, sound-effect, pause and crowd tags, phoneme control for English/Chinese/Japanese, multi-speaker tagging, and settings (temperature/top_p 0.7, speed 0.5-2.0, volume -10..10 dB).","snippet":"Useful for: Voiceover and dialogue writers tuning expressive delivery.\n\nFirst action: Write <b>one</b> sentence with a single bracketed emotion cue before it, add <b>text</b> after any sound-effect","status":"active","categories":["T08"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6S7KSHXWMZZHCTPETPSMXWV","api_url":"https://veyrul.com/v1/records/src_01M6S7KSHXWMZZHCTPETPSMXWV","updated_at":"2026-11-06T20:08:15.643Z","score":0.2075}},{"kind":"record","record":{"id":"src_01M6SGQRAXHMWAEZHZJS8WYKG5","type":"source","title":"VoXtream2: Full-stream TTS with dynamic speaking rate control","summary":"Zero-shot full-stream TTS with speaking rate adjustable mid-utterance, textless audio prompting, 4x faster than real time and 74 ms first-packet latency on a consumer GPU (authors' abstract).","snippet":"first-packet latency on a consumer GPU (authors' abstract).\n\nUseful for: Builders of live <b>narration</b> or voice agents who need rate control.\n\nFirst action: Read the arXiv abstract and follow","status":"active","categories":["T13","T09"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6SGQRAXHMWAEZHZJS8WYKG5","api_url":"https://veyrul.com/v1/records/src_01M6SGQRAXHMWAEZHZJS8WYKG5","updated_at":"2026-11-06T22:47:42.649Z","score":0.2074}},{"kind":"record","record":{"id":"src_01M66QAY5WMXFPC5B0GV7HB6VA","type":"source","title":"MOSS-TTS 1.5 (ComfyUI registry node ComfyUI-MOSS-TTS-1.5)","summary":"ComfyUI node registry custom node pack ComfyUI-MOSS-TTS-1.5 at revision ef9c4808a9f0: latest version 0.6.4; publisher enrico; declared licence {\"file\": \"LICENSE\"}; repository https://github.com/eehrich/ComfyUI-MOSS-TTS-1.5. Metadata-only index entry; not tested guidance.","snippet":"listing, not verified): \"ComfyUI custom nodes for OpenMOSS MOSS-<b>TTS</b> v1.5 — both the <b>Local</b>-Transformer (48 kHz stereo) and the 8B full model (24 kHz mono). Reference-free <b>TTS</b>","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66QAY5WMXFPC5B0GV7HB6VA","api_url":"https://veyrul.com/v1/records/src_01M66QAY5WMXFPC5B0GV7HB6VA","updated_at":"2026-10-30T15:37:28.453Z","score":0.2056}},{"kind":"record","record":{"id":"src_01M6WHNHG7QRTZE8CV4ZBCNBMX","type":"source","title":"dots-studio/dots.tts-mf-1step","summary":"Hugging Face model dots-studio/dots.tts-mf-1step at revision 4e872aa8f47e: text-to-speech; library dots_tts; declared licence apache-2.0; not gated. Metadata-only index entry; not tested guidance.","snippet":"Hugging Face model dots-studio/dots.tts-mf-1step at revision 4e872aa8f47e: <b>text</b>-to-speech; library dots_<b>tts</b>; declared licence apache-2.0; not gated. Metadata-only index entry; not tested","status":"active","categories":["T13"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6WHNHG7QRTZE8CV4ZBCNBMX","api_url":"https://veyrul.com/v1/records/src_01M6WHNHG7QRTZE8CV4ZBCNBMX","updated_at":"2026-11-08T03:01:41.989Z","score":0.2012}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6TYEVR78SCNCRGRY85SQKAK","type":"article","revision":1,"title":"Narrate a text locally with Kokoro TTS, one WAV file per chunk","coverage":"For writers and editors who want local text-to-speech narration with the open-weight Kokoro model and its Python library. You end with numbered WAV files, one per paragraph. It is based on the project README and was not run.","example":"A script reads a chapter text file with a fixed American English voice and writes one WAV per paragraph; this adapted example was not run.","tips":["Match the language code to the voice, and install the extra misaki package for Japanese or Mandarin.","Sample the beginning, middle and end of the set by ear for names said wrongly and sentences cut short.","If unknown words are read oddly or an error mentions espeak, install the espeak-ng system package."],"categories":["T13","T01"],"tags":["kokoro","text-to-speech","tts","narration","espeak-ng","local-audio","audiobook"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiTmFycmF0ZSBhIHRleHQgbG9jYWxseSB3aXRoIEtva29ybyBUVFMsIG9uZSBXQVYgZmlsZSBwZXIgY2h1bmsiLCJ0eXBlcyI6W10sImNhdGVnb3JpZXMiOltdfQ","ordering":"bounded_reference_and_preview_lanes"}