[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BV2X3V5PF68B67Y5M0K8CS":3,"skill-same:01M7BV2X3V5PF68B67Y5M0K8CS":45},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":6,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7BV2X3V5PF68B67Y5M0K8CS","text-to-speech",null,"Produce clean, aligned, delivery-ready TTS segments with loudness normalization, boundary cleanup, and export specs for dubbing.","linyouxue\u002Fskill-repair-benchmark","linyouxue","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F216151464?v=4","01M7BJEVCXKD74KH6FG9CBVSQB","林宥学","01M7BJEVE02NP217V93BKZFC0J",0,"Apache-2.0","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FMMG2Skill-GPT52-Gold31-20260923\u002Ftasks\u002Fmultilingual-video-dubbing\u002Frepaired_skill\u002Ftext-to-speech\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: text-to-speech\ndescription: Produce clean, aligned, delivery-ready TTS segments with loudness normalization,\n  boundary cleanup, and export specs for dubbing.\n---\n\n## Steps\n1. Generate TTS audio per segment using an appropriate engine (neural offline or cloud), then confirm the TTS output’s native sample rate.\n2. Clean up each segment (lightweight, consistent chain):\n   - High-pass around ~20 Hz (rumble\u002FDC removal)\n   - Optional low-pass around ~16 kHz (reduce digital fizz)\n   - Add short fades at boundaries (e.g., ~50 ms) to prevent clicks\n3. Control duration to fit the timing window:\n   - If shorter than the window: **pad silence**\n   - If longer: apply gentle **rate_adjust** (small tempo change) or **trim** carefully\n4. Loudness workflow (ITU-R BS.1770-4 target behavior):\n   - Measure loudness with `ebur128` for reporting\u002Fvalidation.\n   - Normalize as a final step with `loudnorm` (e.g., `I=-23`, `TP=-1.5`, `LRA=11`).\n   - Do **not** rely on `loudnorm` options that may not exist in the environment (notably `measure_only=1` on some FFmpeg builds); use `ebur128` for measurement and `loudnorm` for normalization.\n5. Export delivery audio specs:\n   - Ensure output is **48,000 Hz**, **mono**, and a suitable PCM WAV for segment deliverables (e.g., `pcm_s16le`).\n## Expected Result\nEach TTS segment is clean, click-free, window-aligned with controlled duration (rate_adjust\u002Fpad_silence\u002Ftrim), normalized to a consistent loudness target, and exported as 48 kHz mono audio suitable for muxing into the final dubbed MP4.\n","## Steps\n1. Generate TTS audio per segment using an appropriate engine (neural offline or cloud), then confirm the TTS output’s native sample rate.\n2. Clean up each segment (lightweight, consistent chain):\n   - High-pass around ~20 Hz (rumble\u002FDC removal)\n   - Optional low-pass around ~16 kHz (reduce digital fizz)\n   - Add short fades at boundaries (e.g., ~50 ms) to prevent clicks\n3. Control duration to fit the timing window:\n   - If shorter than the window: **pad silence**\n   - If longer: apply gentle **rate_adjust** (small tempo change) or **trim** carefully\n4. Loudness workflow (ITU-R BS.1770-4 target behavior):\n   - Measure loudness with `ebur128` for reporting\u002Fvalidation.\n   - Normalize as a final step with `loudnorm` (e.g., `I=-23`, `TP=-1.5`, `LRA=11`).\n   - Do **not** rely on `loudnorm` options that may not exist in the environment (notably `measure_only=1` on some FFmpeg builds); use `ebur128` for measurement and `loudnorm` for normalization.\n5. Export delivery audio specs:\n   - Ensure output is **48,000 Hz**, **mono**, and a suitable PCM WAV for segment deliverables (e.g., `pcm_s16le`).\n## Expected Result\nEach TTS segment is clean, click-free, window-aligned with controlled duration (rate_adjust\u002Fpad_silence\u002Ftrim), normalized to a consistent loudness target, and exported as 48 kHz mono audio suitable for muxing into the final dubbed MP4.\n",{"name":5,"description":7},"main","cdcb6d230f3b15c3c33f8a2bdd16439f43602cbe","evaluation\u002Fresults\u002FMMG2Skill-GPT52-Gold31-20260923\u002Ftasks\u002Fmultilingual-video-dubbing\u002Frepaired_skill\u002Ftext-to-speech",1,"https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark","https:\u002F\u002Fgithub.com\u002Flinyouxue","2026-11-14 20:28:35",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add linyouxue\u002Fskill-repair-benchmark --skill text-to-speech",{"tool":37,"command":38},"bunx","bunx skills add linyouxue\u002Fskill-repair-benchmark --skill text-to-speech",{"tool":40,"command":41},"pnpm","pnpm dlx skills add linyouxue\u002Fskill-repair-benchmark --skill text-to-speech","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fevaluation\u002Fresults\u002FMMG2Skill-GPT52-Gold31-20260923\u002Ftasks\u002Fmultilingual-video-dubbing\u002Frepaired_skill\u002Ftext-to-speech\u002FSKILL.md",true,[],[46,53,60,67,72,77],{"skillNo":47,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":50,"categories":51,"keywords":52,"publishedAt":19},"01M7E1HGVRY73NBJ022CJG13X6","video-frame-extraction","Extract frames from video files and save them as images using OpenCV","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":54,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":57,"categories":58,"keywords":59,"publishedAt":19},"01M7E1HAG5R7CJ9C8NYJS771MB","openai-vision","Analyze images and multi-frame sequences using OpenAI GPT vision models","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":61,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7E1H7DADKB6QBWKC2KQ63SZ","image-ocr","Extract text content from images using Tesseract OCR via Python, including structured field extraction from receipts and forms","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_03\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[],{"skillNo":68,"name":48,"nameZh":6,"description":49,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7E1H0WBNT43TENGQY7AVZHD","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fvideo-frame-extraction\u002FSKILL.md",[],[],{"skillNo":73,"name":55,"nameZh":6,"description":56,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7E1GTC7D4N4Q2EF03875J9E","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fopenai-vision\u002FSKILL.md",[],[],{"skillNo":78,"name":62,"nameZh":6,"description":63,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":19},"01M7E1GQ92CWFMGH53KSSE4WER","https:\u002F\u002Fgithub.com\u002Flinyouxue\u002Fskill-repair-benchmark\u002Fblob\u002Fmain\u002Fjpg-ocr-stat\u002Fresult\u002Fskilltta-claude4.7\u002Fgroup_03\u002Frun_02\u002Finputs\u002Fskills\u002Fimage-ocr\u002FSKILL.md",[],[]]