[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-noizai-tts-id":3,"guides-for-noizai-tts":217,"similar-k1746xzw25syqd1mcswezg14k1867vsj":218},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":20,"identity":184,"isFallback":188,"parentExtension":189,"providers":190,"relations":194,"repo":196,"workflow":214},1778054291668.0989,"k1746xzw25syqd1mcswezg14k1867vsj",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Use this skill whenever the user wants to convert text into speech, generate audio from text, or produce voiceovers. Triggers include: any mention of 'TTS', 'text to speech', 'speak', 'say', 'voice', 'read aloud', 'audio narration', 'voiceover', 'dubbing', or requests to turn written content into spoken audio. Also use when converting EPUB/PDF/SRT/articles to audio, cloning voices from reference audio, controlling emotion or speed in speech, aligning speech to subtitle timelines, or producing per-segment voice-mapped audio.",{},"TTS","https://github.com/noizai/skills/tree/HEAD/skills/tts",[15,16,17,18,19],"tts","speech-synthesis","audio-generation","voice-cloning","dubbing",{"_creationTime":21,"_id":22,"extensionId":5,"locale":23,"result":24,"trustSignals":173,"workflow":182},1778054322837.3628,"kn765n9p5psvwdc862wc0a6z3d866c0r","en",{"checks":25,"evaluatedAt":163,"extensionSummary":164,"promptVersionExtension":165,"promptVersionScoring":166,"rationale":167,"score":168,"summary":169,"tags":170,"targetMarket":171,"tier":172},[26,31,34,37,41,44,48,52,55,58,63,67,71,74,77,80,83,86,89,92,96,100,105,109,112,115,118,122,125,128,131,134,137,141,144,147,150,153,156,160],{"category":27,"check":28,"severity":29,"summary":30},"Practical Utility","Problem relevance","pass","The displayed description clearly states the user problem of converting text to speech and generating audio, providing specific use cases like voiceovers, dubbing, and converting various document formats to audio.",{"category":27,"check":32,"severity":29,"summary":33},"Unique selling proposition","The skill offers significant value beyond basic TTS by supporting advanced features like voice cloning, emotion control, precise timeline alignment for dubbing, and integration with chat platforms, which go beyond typical LLM capabilities.",{"category":27,"check":35,"severity":29,"summary":36},"Production readiness","The skill is production-ready, offering both simple text-to-speech and advanced timeline-aligned rendering with clear usage instructions, multiple backends, and detailed documentation for various use cases.",{"category":38,"check":39,"severity":29,"summary":40},"Scope","Single responsibility principle","The extension focuses solely on text-to-speech and related audio generation tasks, including advanced features like voice cloning and timeline rendering, without encroaching on unrelated domains.",{"category":38,"check":42,"severity":29,"summary":43},"Description quality","The displayed description is concise, readable, and accurately reflects the skill's capabilities, including its various modes, triggers, and advanced features.",{"category":45,"check":46,"severity":29,"summary":47},"Invocation","Scoped tools","The script exposes specific commands like 'speak', 'render', 'to-srt', and 'config', each with well-defined arguments, adhering to the principle of narrow verb-noun specialists.",{"category":49,"check":50,"severity":29,"summary":51},"Documentation","Configuration & parameter reference","All parameters for 'speak', 'render', and 'to-srt' commands are documented, including defaults and specific choices. The API key handling is also clearly explained.",{"category":38,"check":53,"severity":29,"summary":54},"Tool naming","Tool names like 'speak', 'render', 'to-srt', and 'config' are descriptive and adhere to the expected command-line style.",{"category":38,"check":56,"severity":29,"summary":57},"Minimal I/O surface","The script's arguments are specific and typed, requesting only necessary data for each operation, and the output is the generated audio file or a status message.",{"category":59,"check":60,"severity":61,"summary":62},"License","License usability","not_applicable","No license file or SPDX identifier was found in the repository.",{"category":64,"check":65,"severity":61,"summary":66},"Maintenance","Commit recency","The last commit date is not available, so this check cannot be performed.",{"category":68,"check":69,"severity":29,"summary":70},"Security","Secret Management","The skill handles API keys securely by storing them in a configuration file with restricted permissions or via environment variables, and does not echo resolved secrets to stdout/stderr.",{"category":68,"check":72,"severity":29,"summary":73},"Injection","The scripts appear to treat input text and file content as data and do not execute instructions embedded within them. No 3rd party data loading or web fetching is used in a way that suggests instruction execution.",{"category":68,"check":75,"severity":29,"summary":76},"Transitive Supply-Chain Grenades","The extension bundles all necessary scripts and does not fetch or execute remote code at runtime. Network calls to the Noiz API are for synthesis, not for loading executable instructions.",{"category":68,"check":78,"severity":29,"summary":79},"Sandbox Isolation","The skill only modifies files within the specified output path or the ~/.config/noiz directory for API key storage. It does not attempt to access or modify files outside its designated scope.",{"category":68,"check":81,"severity":29,"summary":82},"Sandbox escape primitives","No detached process spawns or retry loops around denied tool calls were found in the scripts.",{"category":68,"check":84,"severity":29,"summary":85},"Data Exfiltration","Outbound network calls are documented to the Noiz API for synthesis, and reference audio download URLs are either from trusted sources or user-provided. No evidence of exfiltrating confidential data is present.",{"category":68,"check":87,"severity":29,"summary":88},"Hidden Text Tricks","The bundled files do not contain any hidden-steering tricks, invisible Unicode characters, or other obfuscation methods designed to manipulate the model.",{"category":68,"check":90,"severity":29,"summary":91},"Opaque code execution","The bundled scripts are written in plain Python and are not obfuscated, minified, or dynamically fetched.",{"category":93,"check":94,"severity":29,"summary":95},"Portability","Structural Assumption","The scripts use standard Python practices and command-line arguments, and do not appear to make specific assumptions about user project organization beyond specifying input/output files.",{"category":97,"check":98,"severity":61,"summary":99},"Trust","Issues Attention","No GitHub issues data is available for this check.",{"category":101,"check":102,"severity":103,"summary":104},"Versioning","Release Management","warning","No explicit versioning information (e.g., in SKILL.md, package.json, or CHANGELOG) is present in the repository.",{"category":106,"check":107,"severity":29,"summary":108},"Code Execution","Validation","Input arguments are handled via argparse, providing basic type and choice validation. File paths and URLs are used as input to libraries or commands which handle their own validation.",{"category":68,"check":110,"severity":29,"summary":111},"Unguarded Destructive Operations","The skill is primarily focused on audio generation and does not perform any destructive operations on the user's system.",{"category":106,"check":113,"severity":29,"summary":114},"Error Handling","The Python scripts include try-except blocks and provide informative error messages to stderr, indicating failures gracefully and exiting with non-zero status codes.",{"category":106,"check":116,"severity":29,"summary":117},"Logging","The scripts provide informative messages to stderr regarding progress, configuration, and warnings, serving as a basic form of audit log for user actions.",{"category":119,"check":120,"severity":29,"summary":121},"Compliance","GDPR","The skill processes text for TTS and optionally handles reference audio. It does not appear to operate on personal data without user intent, and network calls to the Noiz API are for synthesis and documented.",{"category":119,"check":123,"severity":29,"summary":124},"Target market","The extension is designed for global use, supporting multiple languages and offering clear instructions for API key configuration and backend selection. No specific regional restrictions were detected.",{"category":93,"check":126,"severity":29,"summary":127},"Runtime stability","The scripts are written in Python 3 and rely on standard libraries or easily installable packages ('requests', 'ffmpeg'), with clear installation instructions provided.",{"category":45,"check":129,"severity":29,"summary":130},"Precise Purpose","The 'name' and 'description' fields in SKILL.md clearly define the purpose of the TTS skill, its triggers, and its capabilities, including specific use cases and explicit boundaries.",{"category":45,"check":132,"severity":29,"summary":133},"Concise Frontmatter","The frontmatter in SKILL.md is concise, clearly stating the core capability and providing relevant trigger phrases without excessive keyword stuffing.",{"category":49,"check":135,"severity":29,"summary":136},"Concise Body","The SKILL.md body is well-structured and reasonably concise, delegating detailed references and third-party integration information to separate files.",{"category":138,"check":139,"severity":29,"summary":140},"Context","Progressive Disclosure","Detailed references and third-party integration guides are provided in separate Markdown files (`ref_3rd_party.md`, `reference.md`), allowing for progressive disclosure of information.",{"category":138,"check":142,"severity":61,"summary":143},"Forked exploration","This skill does not involve deep exploration or multi-file inspection, so the 'context: fork' setting is not applicable.",{"category":27,"check":145,"severity":29,"summary":146},"Usage examples","The SKILL.md file provides clear, end-to-end usage examples for basic TTS, voice cloning, SRT generation, and timeline rendering, demonstrating input, invocation, and expected outcomes.",{"category":27,"check":148,"severity":29,"summary":149},"Edge cases","The skill handles edge cases such as empty input text, missing API keys (with fallback to guest mode), and long text inputs with warnings. Failure modes for backend operations are reported.",{"category":106,"check":151,"severity":29,"summary":152},"Tool Fallback","The Noiz backend gracefully falls back to 'noiz-guest' mode when no API key is configured, providing limited functionality without requiring explicit user action.",{"category":93,"check":154,"severity":29,"summary":155},"Stack assumptions","The skill clearly states its requirements, including Python 3.6+, 'requests' package for Noiz, and 'ffmpeg' for timeline mode, along with installation instructions.",{"category":157,"check":158,"severity":29,"summary":159},"Safety","Halt on unexpected state","The scripts perform input validation and report errors clearly to stderr, halting execution on unexpected states like empty input or missing configurations, rather than proceeding with destructive or incorrect actions.",{"category":93,"check":161,"severity":29,"summary":162},"Cross-skill coupling","The TTS skill operates independently and does not implicitly rely on other skills. It focuses solely on its defined text-to-speech and audio generation functionalities.",1778054320499,"This skill converts text into speech using either the Noiz cloud API or a local Kokoro backend. It supports simple text-to-speech, voice cloning from reference audio, and advanced timeline-accurate audio rendering for dubbing or narration, with clear command-line interfaces and fallback mechanisms.","2.0.0","3.4.0","The TTS skill is highly polished, offering robust functionality with clear documentation, secure secret management, and comprehensive error handling. The only minor deduction comes from the lack of explicit versioning information.",95,"A highly capable and well-documented text-to-speech skill supporting various backends, advanced features like voice cloning and timeline rendering, and secure operation.",[15,16,17,18,19],"global","verified",{"codeQuality":174,"collectedAt":175,"documentation":176,"maintenance":178,"security":179,"testCoverage":181},{},1778054306802,{"descriptionLength":177,"readmeSize":8},529,{},{"hasNpmPackage":180,"smitheryVerified":180},false,{"hasCi":180,"hasTests":180},{"updatedAt":183},1778054322837,{"githubOwner":185,"githubRepo":186,"locale":23,"slug":15,"type":187},"noizai","skills","skill",true,null,{"extract":191,"llm":193},{"commitSha":192,"license":61},"3428725f8c34e2179e0bdaf4c441697e0014d289",{"promptVersionExtension":165,"promptVersionScoring":166,"score":168,"targetMarket":171,"tier":172},{"repoId":195},"kd76a0e9dvgjrpvm0qe8k24qy18653ah",{"_creationTime":197,"_id":195,"identity":198,"providers":200,"workflow":211},1777995558409.862,{"githubOwner":185,"githubRepo":186,"sourceUrl":199},"https://github.com/noizai/skills",{"discover":201,"github":204},{"sources":202},[203],"skills-sh",{"closedIssues90d":8,"forks":205,"openIssues90d":206,"pushedAt":207,"readmeSize":208,"stars":209,"topics":210},69,2,1776527927000,4484,490,[],{"discoverAt":212,"extractAt":213,"githubAt":213,"updatedAt":213},1777995558409,1778054292661,{"anyEnrichmentAt":215,"extractAt":216,"githubAt":215,"llmAt":183,"updatedAt":183},1778054291966,1778054291668,[],[219,248,277,301,337,359],{"_creationTime":220,"_id":221,"community":222,"display":223,"identity":232,"providers":236,"relations":242,"workflow":244},1778053100136.245,"k17a8rwjmp1sgctvjpwerece6d867cte",{"reviewCount":8},{"description":224,"installMethods":225,"name":226,"sourceUrl":227,"tags":228},"Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.",{},"Podcast Generation Skill","https://github.com/bytedance/deer-flow/tree/HEAD/skills/public/podcast-generation",[229,17,15,230,231],"podcast","python","conversational-ai",{"githubOwner":233,"githubRepo":234,"locale":23,"slug":235,"type":187},"bytedance","deer-flow","podcast-generation",{"extract":237,"llm":240},{"commitSha":238,"license":239},"1336872b15c25d45ebcb7c1cf72369c2bdd53187","MIT",{"promptVersionExtension":165,"promptVersionScoring":166,"score":241,"targetMarket":171,"tier":172},90,{"repoId":243},"kd789sm7egx1h0t1jag6zzhcq98656wv",{"anyEnrichmentAt":245,"extractAt":246,"githubAt":245,"llmAt":247,"updatedAt":247},1778053101076,1778053100136,1778053169012,{"_creationTime":249,"_id":250,"community":251,"display":252,"identity":262,"providers":266,"relations":271,"workflow":273},1778053622473.6453,"k174xmaemtbdy32kf1f0x0rxs1867k5k",{"reviewCount":8},{"description":253,"installMethods":254,"name":255,"sourceUrl":256,"tags":257},"Convert written documents to narrated video scripts with TTS audio and word-level timing. Use when preparing essays, blog posts, or articles for video narration. Outputs scene files, audio, and VTT with precise word timestamps. Keywords: narration, voiceover, TTS, scenes, audio, timing, video script, spoken.",{},"Document to Narration","https://github.com/jwynia/agent-skills/tree/HEAD/skills/education/document-to-narration",[15,258,259,260,17,261],"narration","video-production","scripting","transcription",{"githubOwner":263,"githubRepo":264,"locale":23,"slug":265,"type":187},"jwynia","agent-skills","document-to-narration",{"extract":267,"llm":269},{"commitSha":268,"license":239},"e02ec7e226a6e4f8419fd3b88a1d8e472d421b32",{"promptVersionExtension":165,"promptVersionScoring":166,"score":270,"targetMarket":171,"tier":172},88,{"repoId":272},"kd7efn3mprpa8rd8vm5hw5ebzx864fph",{"anyEnrichmentAt":274,"extractAt":275,"githubAt":274,"llmAt":276,"updatedAt":276},1778053625386,1778053622473,1778054012696,{"_creationTime":278,"_id":279,"community":280,"display":281,"identity":291,"providers":293,"relations":299,"workflow":300},1778054291668.0994,"k17axd8fch27xnebp2qj8j63tx866dkb",{"reviewCount":8},{"description":282,"installMethods":283,"name":284,"sourceUrl":285,"tags":286},"Translate and dub videos from one language to another, replacing the original audio with TTS while keeping the video intact.",{},"Video Translation","https://github.com/noizai/skills/tree/HEAD/skills/video-translation",[287,288,19,15,289,290],"video","translation","youtube","ffmpeg",{"githubOwner":185,"githubRepo":186,"locale":23,"slug":292,"type":187},"video-translation",{"extract":294,"llm":296},{"commitSha":192,"license":295},"n/a",{"promptVersionExtension":165,"promptVersionScoring":166,"score":297,"targetMarket":171,"tier":298},45,"flagged",{"repoId":195},{"anyEnrichmentAt":215,"extractAt":216,"githubAt":215,"llmAt":183,"updatedAt":183},{"_creationTime":302,"_id":303,"community":304,"display":305,"identity":321,"providers":325,"relations":330,"workflow":333},1778053197391.382,"k170wvt5rx3c1hv9a5sfkyezc1866k0q",{"reviewCount":8},{"description":306,"installMethods":307,"name":308,"sourceUrl":309,"tags":310},"Universal AI voice / text-to-speech skill supporting OpenAI TTS (gpt-4o-mini-tts, tts-1), ElevenLabs multilingual TTS with voice cloning, Bailian Qwen TTS (qwen-tts / qwen3-tts-vd with voice-design custom voices, long-text chunking built in), MiniMax speech-02-hd, SiliconFlow CosyVoice / SenseVoice, and PlayHT 2.0. Use this skill whenever the user asks to read text aloud, synthesize speech, generate narration, create voice-over, dub a script, or turn any text into audio (mp3 / wav / ogg / flac). Typical phrases include \"read this aloud\", \"generate voice for ...\", \"create a narration of ...\", \"tts this\", \"把这段念出来\", \"做个配音\", \"合成语音\", or mentions of voices / TTS model names like Alloy, Ash, Cherry, Rachel, CosyVoice, PlayHT. Always use this skill even if the user does not specify a provider — pick one from EXTEND.md defaults or available env keys.",{},"Happy Audio Gen","https://github.com/iamzhihuix/happy-claude-skills/tree/HEAD/skills/happy-audio-gen",[15,311,312,313,314,315,316,317,318,319,320],"speech","audio","voice-generation","openai","elevenlabs","bailian","minimax","siliconflow","playht","bun",{"githubOwner":322,"githubRepo":323,"locale":23,"slug":324,"type":187},"iamzhihuix","happy-claude-skills","happy-audio-gen",{"extract":326,"llm":328},{"commitSha":327,"license":239},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd",{"promptVersionExtension":165,"promptVersionScoring":166,"score":329,"targetMarket":171,"tier":172},100,{"parentExtensionId":331,"repoId":332},"k173ydbbp6c0vdpxv5r0q9yvgd867en5","kd7dbbtdq95nkcs3k7fg9w6fdn864j0b",{"anyEnrichmentAt":334,"extractAt":335,"githubAt":334,"llmAt":336,"updatedAt":336},1778053199195,1778053197391,1778053284450,{"_creationTime":338,"_id":339,"community":340,"display":341,"identity":351,"providers":353,"relations":357,"workflow":358},1778054291668.0964,"k17477k0d5jgrwmqqkgp1phgen866eck",{"reviewCount":8},{"description":342,"installMethods":343,"name":344,"sourceUrl":345,"tags":346},"Use this skill whenever the user wants speech to sound more human, companion-like, or emotionally expressive. Triggers include: any mention of 'say like', 'talk like', 'speak like', 'companion voice', 'comfort me', 'cheer me up', 'sound more human', 'good night voice', 'good morning voice', or requests to add fillers, emotion, or personality to generated speech. Also use when the user wants to mimic a specific character's voice, apply speaking style presets (goodnight, morning, comfort, celebration, chatting), tune emotional parameters like warmth or tenderness, or make TTS output feel like a real person talking. If the user asks for a 'voice message', 'companion audio', 'character voice', or wants speech that sighs, laughs, hesitates, or sounds genuinely warm, use this skill. Do NOT use for plain text-to-speech without personality, music generation, sound effects, or general coding tasks unrelated to expressive speech.",{},"Characteristic Voice","https://github.com/noizai/skills/tree/HEAD/skills/characteristic-voice",[15,311,347,348,349,350],"voice","emotion","companion","script",{"githubOwner":185,"githubRepo":186,"locale":23,"slug":352,"type":187},"characteristic-voice",{"extract":354,"llm":355},{"commitSha":192,"license":61},{"promptVersionExtension":165,"promptVersionScoring":166,"score":356,"targetMarket":171,"tier":172},98,{"repoId":195},{"anyEnrichmentAt":215,"extractAt":216,"githubAt":215,"llmAt":183,"updatedAt":183},{"_creationTime":360,"_id":361,"community":362,"display":363,"identity":372,"providers":374,"relations":378,"workflow":380},1778054691785.2524,"k1712xyy3wyvy83c0f9z7kccg9866jg4",{"reviewCount":8},{"description":364,"installMethods":365,"name":366,"sourceUrl":367,"tags":368},"Implement text-to-speech (TTS) capabilities using the z-ai-web-dev-sdk. Use this skill when the user needs to convert text into natural-sounding speech, create audio content, build voice-enabled applications, or generate spoken audio files. Supports multiple voices, adjustable speed, and various audio formats.",{},"Text-to-Speech (TTS)","https://github.com/answerzhao/agent-skills/tree/HEAD/glm-skills/TTS",[15,369,312,370,371],"text-to-speech","sdk","z-ai-web-dev-sdk",{"githubOwner":373,"githubRepo":264,"locale":23,"slug":15,"type":187},"answerzhao",{"extract":375,"llm":377},{"commitSha":376,"license":239},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":165,"promptVersionScoring":166,"score":168,"targetMarket":171,"tier":172},{"repoId":379},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":381,"extractAt":382,"githubAt":381,"llmAt":383,"updatedAt":383},1778054692243,1778054691785,1778054738050]