[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-noizai-characteristic-voice-id":3,"guides-for-noizai-characteristic-voice":221,"similar-k17477k0d5jgrwmqqkgp1phgen866eck":222},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":187,"isFallback":192,"parentExtension":193,"providers":194,"relations":198,"repo":200,"workflow":218},1778054291668.0964,"k17477k0d5jgrwmqqkgp1phgen866eck",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"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",[15,16,17,18,19,20],"tts","speech","voice","emotion","companion","script",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":176,"workflow":185},1778054322837.3599,"kn78m991nw2zt3hf4zfp7y8m4n867xt4","en",{"checks":26,"evaluatedAt":166,"extensionSummary":167,"promptVersionExtension":168,"promptVersionScoring":169,"rationale":170,"score":171,"summary":172,"tags":173,"targetMarket":174,"tier":175},[27,32,35,38,42,45,50,54,57,60,64,68,71,75,78,81,84,87,90,93,96,100,104,108,112,115,118,121,125,128,131,134,137,140,144,147,150,153,156,159,163],{"category":28,"check":29,"severity":30,"summary":31},"Practical Utility","Problem relevance","pass","The description clearly identifies the user problem of making speech sound more human, companion-like, or emotionally expressive, and provides specific triggers and non-goals.",{"category":28,"check":33,"severity":30,"summary":34},"Unique selling proposition","The skill offers unique value by providing specific techniques like non-lexical fillers and emotion tuning, along with presets and character voice cloning, which go beyond basic text-to-speech.",{"category":28,"check":36,"severity":30,"summary":37},"Production readiness","The skill is production-ready, offering a complete lifecycle for generating expressive speech with clear prerequisites, backend options (local/remote), and credential management.",{"category":39,"check":40,"severity":30,"summary":41},"Scope","Single responsibility principle","The extension focuses on a single domain: making speech sound more human and expressive, with clear sub-capabilities like fillers, emotion tuning, and voice cloning.",{"category":39,"check":43,"severity":30,"summary":44},"Description quality","The description is accurate, well-structured, and clearly explains the skill's purpose, triggers, and usage.",{"category":46,"check":47,"severity":48,"summary":49},"Invocation","Scoped tools","not_applicable","This skill does not expose individual tools; it is invoked via a bash script with various options.",{"category":51,"check":52,"severity":30,"summary":53},"Documentation","Configuration & parameter reference","All necessary parameters, including API keys, backend choices, and script options, are clearly documented with installation hints and usage examples.",{"category":39,"check":55,"severity":48,"summary":56},"Tool naming","The skill is invoked via a script, not individual tools with specific names.",{"category":39,"check":58,"severity":30,"summary":59},"Minimal I/O surface","The script's arguments are well-defined and specific, requesting only necessary inputs like text, output file, and configuration options.",{"category":61,"check":62,"severity":48,"summary":63},"License","License usability","No license information was found in the repository.",{"category":65,"check":66,"severity":48,"summary":67},"Maintenance","Commit recency","No commit history is available for evaluation.",{"category":65,"check":69,"severity":30,"summary":70},"Dependency Management","The skill lists its external dependencies (curl, python3, etc.) and provides installation hints, allowing users to manage them manually.",{"category":72,"check":73,"severity":30,"summary":74},"Security","Secret Management","The API key is handled via a script that saves it to a secure file with restricted permissions (~/.noiz_api_key, mode 600) and does not echo it to stdout.",{"category":72,"check":76,"severity":30,"summary":77},"Injection","The script handles user-provided text and audio files as data, and there are no indications of executing arbitrary code from these inputs.",{"category":72,"check":79,"severity":30,"summary":80},"Transitive Supply-Chain Grenades","The skill bundles all necessary scripts and dependencies. It does not fetch or execute external code at runtime.",{"category":72,"check":82,"severity":30,"summary":83},"Sandbox Isolation","The script interacts with user-provided files and a local API key file, but all paths are relative or standard user directories, and it does not attempt to modify files outside its scope.",{"category":72,"check":85,"severity":30,"summary":86},"Sandbox escape primitives","No detached processes or deny-retry loops were found in the provided script.",{"category":72,"check":88,"severity":30,"summary":89},"Data Exfiltration","The skill clearly documents when data (text, reference audio) is sent to the Noiz backend and provides a local Kokoro backend option for offline processing. No other undocumented outbound calls are apparent.",{"category":72,"check":91,"severity":30,"summary":92},"Hidden Text Tricks","The bundled files do not contain any hidden text tricks, invisible characters, or obfuscated instructions.",{"category":72,"check":94,"severity":30,"summary":95},"Opaque code execution","The provided bash script is readable and does not use obfuscation techniques like base64 payloads or runtime code fetching.",{"category":97,"check":98,"severity":30,"summary":99},"Portability","Structural Assumption","The script correctly uses standard paths like `$HOME/.noiz_api_key` and refers to skill-local files via relative paths, making it portable.",{"category":101,"check":102,"severity":48,"summary":103},"Trust","Issues Attention","No issue tracker data is available for this skill.",{"category":105,"check":106,"severity":48,"summary":107},"Versioning","Release Management","No versioning information (manifest version, Git tags, CHANGELOG) was found.",{"category":109,"check":110,"severity":30,"summary":111},"Code Execution","Validation","The bash script uses `set -euo pipefail` for basic error handling and argument parsing, and the CLI arguments are processed with explicit checks.",{"category":72,"check":113,"severity":30,"summary":114},"Unguarded Destructive Operations","The skill is primarily focused on audio generation and does not perform any destructive operations.",{"category":109,"check":116,"severity":30,"summary":117},"Error Handling","The bash script includes error handling for argument parsing, backend detection, API key loading, and external tool execution, exiting with non-zero status on failure.",{"category":109,"check":119,"severity":30,"summary":120},"Logging","The script provides informative output to stderr regarding its progress, such as backend selection, voice selection, and success/error messages.",{"category":122,"check":123,"severity":30,"summary":124},"Compliance","GDPR","The skill clearly documents its data transmission policies for both the Noiz and Kokoro backends, including what data is sent and where, allowing users to make informed decisions.",{"category":122,"check":126,"severity":30,"summary":127},"Target market","The extension is generally global in scope, with options for local processing (Kokoro) and documented data transmission for the Noiz backend. No specific regional limitations are imposed.",{"category":97,"check":129,"severity":30,"summary":130},"Runtime stability","The script clearly lists its runtime requirements (curl, python3) and provides hints for optional dependencies, ensuring it runs in environments where these are available.",{"category":46,"check":132,"severity":30,"summary":133},"Precise Purpose","The description clearly defines the purpose (human-like, companion-like speech) and provides explicit triggers and non-goals, making its scope precise.",{"category":46,"check":135,"severity":30,"summary":136},"Concise Frontmatter","The frontmatter is dense and effectively summarizes the core capability and triggers within a reasonable character count.",{"category":51,"check":138,"severity":30,"summary":139},"Concise Body","The SKILL.md body is concise, delegating detailed prerequisites and usage to separate sections and the script's help message.",{"category":141,"check":142,"severity":30,"summary":143},"Context","Progressive Disclosure","Detailed information such as prerequisites and configuration is presented in distinct sections within SKILL.md, and further command-line options are available via `--help`.",{"category":141,"check":145,"severity":48,"summary":146},"Forked exploration","The skill is a direct execution script and does not involve exploratory tasks that would benefit from forked context.",{"category":28,"check":148,"severity":30,"summary":149},"Usage examples","The documentation provides multiple, ready-to-use examples demonstrating various presets, options, and backend usage, with clear invocations and expected outcomes.",{"category":28,"check":151,"severity":30,"summary":152},"Edge cases","The documentation covers potential issues like API key configuration, backend availability, and the need for manual installation of dependencies, with clear recovery steps.",{"category":109,"check":154,"severity":30,"summary":155},"Tool Fallback","The script offers a fallback to the local Kokoro backend if the Noiz API key is not configured, and it clearly lists the requirements for each backend.",{"category":97,"check":157,"severity":30,"summary":158},"Stack assumptions","The script explicitly states its runtime requirements (curl, python3) and provides hints for optional dependencies, making its stack assumptions clear.",{"category":160,"check":161,"severity":30,"summary":162},"Safety","Halt on unexpected state","The bash script uses `set -euo pipefail` for robust error handling, halting execution on unexpected states or errors.",{"category":97,"check":164,"severity":30,"summary":165},"Cross-skill coupling","The skill is self-contained and does not appear to rely on other skills being loaded in the same session.",1778054306463,"This skill uses a bash script to interact with either the Noiz AI backend or a local Kokoro TTS backend for text-to-speech generation. It supports presets for different speaking styles, custom emotion and speed tuning, and voice cloning using reference audio. The script handles API key management and clearly outlines prerequisites.","2.0.0","3.4.0","The skill is exceptionally well-documented and robust, with clear explanations, practical examples, and strong security and error handling practices. The only minor deductions are the lack of explicit versioning and the absence of license information.",98,"This skill provides a robust and user-friendly way to generate human-like, emotionally expressive speech with various presets and options.",[15,16,17,18,19,20],"global","verified",{"codeQuality":177,"collectedAt":178,"documentation":179,"maintenance":181,"security":182,"testCoverage":184},{},1778054293450,{"descriptionLength":180,"readmeSize":8},933,{},{"hasNpmPackage":183,"smitheryVerified":183},false,{"hasCi":183,"hasTests":183},{"updatedAt":186},1778054322837,{"githubOwner":188,"githubRepo":189,"locale":24,"slug":190,"type":191},"noizai","skills","characteristic-voice","skill",true,null,{"extract":195,"llm":197},{"commitSha":196,"license":48},"3428725f8c34e2179e0bdaf4c441697e0014d289",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":199},"kd76a0e9dvgjrpvm0qe8k24qy18653ah",{"_creationTime":201,"_id":199,"identity":202,"providers":204,"workflow":215},1777995558409.862,{"githubOwner":188,"githubRepo":189,"sourceUrl":203},"https://github.com/noizai/skills",{"discover":205,"github":208},{"sources":206},[207],"skills-sh",{"closedIssues90d":8,"forks":209,"openIssues90d":210,"pushedAt":211,"readmeSize":212,"stars":213,"topics":214},69,2,1776527927000,4484,490,[],{"discoverAt":216,"extractAt":217,"githubAt":217,"updatedAt":217},1777995558409,1778054292661,{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":186,"updatedAt":186},1778054291966,1778054291668,[],[223,259,282,310,333,359],{"_creationTime":224,"_id":225,"community":226,"display":227,"identity":242,"providers":246,"relations":252,"workflow":255},1778053197391.382,"k170wvt5rx3c1hv9a5sfkyezc1866k0q",{"reviewCount":8},{"description":228,"installMethods":229,"name":230,"sourceUrl":231,"tags":232},"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",[15,16,233,234,235,236,237,238,239,240,241],"audio","voice-generation","openai","elevenlabs","bailian","minimax","siliconflow","playht","bun",{"githubOwner":243,"githubRepo":244,"locale":24,"slug":245,"type":191},"iamzhihuix","happy-claude-skills","happy-audio-gen",{"extract":247,"llm":250},{"commitSha":248,"license":249},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd","MIT",{"promptVersionExtension":168,"promptVersionScoring":169,"score":251,"targetMarket":174,"tier":175},100,{"parentExtensionId":253,"repoId":254},"k173ydbbp6c0vdpxv5r0q9yvgd867en5","kd7dbbtdq95nkcs3k7fg9w6fdn864j0b",{"anyEnrichmentAt":256,"extractAt":257,"githubAt":256,"llmAt":258,"updatedAt":258},1778053199195,1778053197391,1778053284450,{"_creationTime":260,"_id":261,"community":262,"display":263,"identity":272,"providers":274,"relations":280,"workflow":281},1778054291668.097,"k170fae6s3s4fwfbye7ys93sf5867w6j",{"reviewCount":8},{"description":264,"installMethods":265,"name":266,"sourceUrl":267,"tags":268},"Chat with any real person or fictional character in their own voice by automatically finding their speech online, extracting a clean reference sample, and generating audio replies. Also supports generating a matching voice from an uploaded image. Use when the user says \"我想跟xxx聊天\", \"你来扮演xxx跟我说话\", \"让xxx给我讲讲这篇文章\", \"我想跟图片中的人说话\", or similar.",{},"Chat with Anyone","https://github.com/noizai/skills/tree/HEAD/skills/chat-with-anyone",[17,15,269,233,270,271],"cloning","ai","character",{"githubOwner":188,"githubRepo":189,"locale":24,"slug":273,"type":191},"chat-with-anyone",{"extract":275,"llm":277},{"commitSha":196,"license":276},"critical",{"promptVersionExtension":168,"promptVersionScoring":169,"score":278,"targetMarket":174,"tier":279},85,"flagged",{"repoId":199},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":186,"updatedAt":186},{"_creationTime":283,"_id":284,"community":285,"display":286,"identity":297,"providers":300,"relations":304,"workflow":306},1778053148350.4797,"k170wp3p5gmtvqjsex8qpeymtn867nc8",{"reviewCount":8},{"description":287,"installMethods":288,"name":289,"sourceUrl":290,"tags":291},"Automate SMS communications, two-way messaging, notifications, and voice workflows with Twilio",{},"Twilio SMS Automation","https://github.com/claude-office-skills/skills/tree/HEAD/twilio-sms",[292,293,294,17,295,296],"twilio","sms","messaging","automation","communication",{"githubOwner":298,"githubRepo":189,"locale":24,"slug":299,"type":191},"claude-office-skills","twilio-sms-automation",{"extract":301,"llm":303},{"commitSha":302,"license":249},"9c4c7d5cd2813a8936bf2c9fdb174ea883b85a11",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":305},"kd7fw7xbj58qc2z8whrrjptbed8659db",{"anyEnrichmentAt":307,"extractAt":308,"githubAt":307,"llmAt":309,"updatedAt":309},1778053151766,1778053148350,1778053561145,{"_creationTime":311,"_id":312,"community":313,"display":314,"identity":322,"providers":323,"relations":327,"workflow":329},1778053440456.6604,"k17a2cxtswmmk54b8wmpfbp5f9866jr0",{"reviewCount":8},{"description":315,"installMethods":316,"name":317,"sourceUrl":318,"tags":319},"Convert text to speech using ElevenLabs voice AI. Use when generating audio from text, creating voiceovers, building voice apps, or synthesizing speech in 70+ languages.",{},"ElevenLabs Text-to-Speech","https://github.com/elevenlabs/skills/tree/HEAD/text-to-speech",[320,236,17,233,321],"text-to-speech","synthesis",{"githubOwner":236,"githubRepo":189,"locale":24,"slug":320,"type":191},{"extract":324,"llm":326},{"commitSha":325,"license":249},"b476f0ccf4be0e22b2e77cc39307665425d1472b",{"promptVersionExtension":168,"promptVersionScoring":169,"score":171,"targetMarket":174,"tier":175},{"repoId":328},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"anyEnrichmentAt":330,"extractAt":331,"githubAt":330,"llmAt":332,"updatedAt":332},1778053440833,1778053440456,1778053480675,{"_creationTime":334,"_id":335,"community":336,"display":337,"identity":345,"providers":348,"relations":353,"workflow":355},1778054691785.2524,"k1712xyy3wyvy83c0f9z7kccg9866jg4",{"reviewCount":8},{"description":338,"installMethods":339,"name":340,"sourceUrl":341,"tags":342},"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",[15,320,233,343,344],"sdk","z-ai-web-dev-sdk",{"githubOwner":346,"githubRepo":347,"locale":24,"slug":15,"type":191},"answerzhao","agent-skills",{"extract":349,"llm":351},{"commitSha":350,"license":249},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":168,"promptVersionScoring":169,"score":352,"targetMarket":174,"tier":175},95,{"repoId":354},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":356,"extractAt":357,"githubAt":356,"llmAt":358,"updatedAt":358},1778054692243,1778054691785,1778054738050,{"_creationTime":360,"_id":361,"community":362,"display":363,"identity":373,"providers":374,"relations":377,"workflow":378},1778054291668.0989,"k1746xzw25syqd1mcswezg14k1867vsj",{"reviewCount":8},{"description":364,"installMethods":365,"name":366,"sourceUrl":367,"tags":368},"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",[15,369,370,371,372],"speech-synthesis","audio-generation","voice-cloning","dubbing",{"githubOwner":188,"githubRepo":189,"locale":24,"slug":15,"type":191},{"extract":375,"llm":376},{"commitSha":196,"license":48},{"promptVersionExtension":168,"promptVersionScoring":169,"score":352,"targetMarket":174,"tier":175},{"repoId":199},{"anyEnrichmentAt":219,"extractAt":220,"githubAt":219,"llmAt":186,"updatedAt":186}]