[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"extension-skill-aahl-edge-tts-vi":3,"guides-for-aahl-edge-tts":229,"similar-k170rzj5b63rat15sg81fqcqyx867e52":230},{"_creationTime":4,"_id":5,"children":6,"community":7,"display":9,"evaluation":21,"identity":186,"isFallback":190,"parentExtension":191,"providers":192,"relations":197,"repo":199,"workflow":226},1778054061126.638,"k170rzj5b63rat15sg81fqcqyx867e52",[],{"reviewCount":8},0,{"description":10,"installMethods":11,"name":12,"sourceUrl":13,"tags":14},"Text-to-speech conversion using `uvx edge-tts` for generating audio from text. Use when (1) User requests audio/voice output with the \"tts\" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, driving, cooking). (3) User wants a specific voice, speed, pitch, or format for TTS output.",{},"Edge TTS","https://github.com/aahl/skills/tree/HEAD/skills/edge-tts",[15,16,17,18,19,20],"tts","audio","text-to-speech","uvx","edge-tts","microsoft",{"_creationTime":22,"_id":23,"extensionId":5,"locale":24,"result":25,"trustSignals":175,"workflow":184},1778054102990.6836,"kn7dpe2ckpzvd4h03c0fctw6js866pbv","en",{"checks":26,"evaluatedAt":165,"extensionSummary":166,"promptVersionExtension":167,"promptVersionScoring":168,"rationale":169,"score":170,"summary":171,"tags":172,"targetMarket":173,"tier":174},[27,32,35,39,43,47,51,55,60,64,68,71,74,77,80,84,87,90,93,96,100,104,107,111,114,117,120,123,126,129,132,135,139,143,146,149,152,155,159,162],{"category":28,"check":29,"severity":30,"summary":31},"Invocation","Precise Purpose","pass","The description clearly states that the skill performs text-to-speech conversion using `uvx edge-tts`, and provides specific triggers and use cases such as 'User requests audio/voice output with the \"tts\" trigger or keyword' and 'Content needs to be spoken rather than read'.",{"category":28,"check":33,"severity":30,"summary":34},"Concise Frontmatter","The frontmatter is concise and effectively summarizes the core capability and triggers within the expected character limit.",{"category":36,"check":37,"severity":30,"summary":38},"Documentation","Concise Body","The SKILL.md body is concise, providing usage examples and voice information without excessive length, and defers to external commands for listing all voices.",{"category":40,"check":41,"severity":30,"summary":42},"Context","Progressive Disclosure","The SKILL.md outlines the core usage and provides examples of command-line arguments. Detailed information like available voices is presented directly, and the command to list all voices is provided, which is a form of progressive disclosure for complex data.",{"category":40,"check":44,"severity":45,"summary":46},"Forked exploration","not_applicable","This skill is a short-form tool for generating audio and does not involve deep exploration or multi-file inspection, making the 'context: fork' setting not applicable.",{"category":48,"check":49,"severity":30,"summary":50},"Practical Utility","Usage examples","The SKILL.md provides clear, end-to-end examples for basic TTS, with subtitles, changing rate/volume/pitch, and changing voices, demonstrating the claimed output.",{"category":48,"check":52,"severity":53,"summary":54},"Edge cases","info","The skill handles common TTS parameters like rate, volume, pitch, and voice selection. However, it does not explicitly document failure modes such as invalid voice names or unavailable languages, only naming the available ones.",{"category":56,"check":57,"severity":58,"summary":59},"Code Execution","Tool Fallback","warning","The skill explicitly requires the `uvx edge-tts` command, which is indicated by the `![Require](https://img.shields.io/badge/uvx-+?label=bin)` badge. There is no declared fallback or mention of its optionality.",{"category":61,"check":62,"severity":30,"summary":63},"Portability","Stack assumptions","The skill's usage examples clearly indicate the reliance on the `uvx edge-tts` command-line tool, implicitly defining the execution environment.",{"category":65,"check":66,"severity":45,"summary":67},"Safety","Halt on unexpected state","The skill's primary function is to execute a command-line tool for TTS generation. It does not appear to have complex pre-state requirements or destructive operations that would necessitate explicit halting on unexpected state.",{"category":61,"check":69,"severity":45,"summary":70},"Cross-skill coupling","This skill is self-contained and focused on TTS generation, not implicitly relying on or coordinating with other skills.",{"category":48,"check":72,"severity":30,"summary":73},"Problem relevance","The description clearly names the problem of needing audio/voice output and explicitly lists use cases like multitasking and accessibility.",{"category":48,"check":75,"severity":30,"summary":76},"Unique selling proposition","The extension leverages `uvx edge-tts` to provide advanced TTS capabilities like specific voice selection, speed, and pitch control, which goes beyond basic LLM text generation and offers tangible value.",{"category":48,"check":78,"severity":30,"summary":79},"Production readiness","The skill is production-ready as it relies on an established command-line tool for its core functionality and provides clear usage examples.",{"category":81,"check":82,"severity":30,"summary":83},"Scope","Single responsibility principle","The extension focuses solely on text-to-speech conversion using `uvx edge-tts`, adhering to a single responsibility.",{"category":81,"check":85,"severity":30,"summary":86},"Description quality","The description is accurate, concise, and clearly explains the purpose and usage of the text-to-speech conversion skill.",{"category":28,"check":88,"severity":30,"summary":89},"Scoped tools","The skill uses the `uvx edge-tts` command directly, acting as a specific tool for TTS generation.",{"category":81,"check":91,"severity":30,"summary":92},"Tool naming","The skill is named 'edge-tts' which is descriptive of its function.",{"category":81,"check":94,"severity":30,"summary":95},"Minimal I/O surface","The skill takes text as input and produces an audio file as output, with parameters for voice, rate, and pitch, which is a well-defined I/O surface.",{"category":97,"check":98,"severity":30,"summary":99},"License","License usability","A clear MIT license is provided in the LICENSE file, which is a permissive open-source license.",{"category":101,"check":102,"severity":45,"summary":103},"Maintenance","Commit recency","No commit history is available for evaluation.",{"category":101,"check":105,"severity":58,"summary":106},"Dependency Management","The skill relies on the external `uvx edge-tts` command-line tool, but there is no explicit mention of how this dependency is managed, updated, or checked for vulnerabilities.",{"category":108,"check":109,"severity":45,"summary":110},"Security","Secret Management","The skill does not appear to handle any secrets or sensitive credentials.",{"category":108,"check":112,"severity":30,"summary":113},"Injection","The skill executes a specific command-line tool with parameters; there's no indication of loading untrusted data as instructions.",{"category":108,"check":115,"severity":30,"summary":116},"Transitive Supply-Chain Grenades","The skill calls a specific command-line tool, and all necessary components appear to be bundled or readily available, with no runtime downloads or remote execution of arbitrary content.",{"category":108,"check":118,"severity":30,"summary":119},"Sandbox Isolation","The skill interacts with a command-line tool that is assumed to operate within its own environment, and there are no indications of file system modifications outside of expected output.",{"category":108,"check":121,"severity":30,"summary":122},"Sandbox escape primitives","The skill executes a single command and does not exhibit patterns indicative of sandbox escape primitives like detached processes or retry loops around denied calls.",{"category":108,"check":124,"severity":30,"summary":125},"Data Exfiltration","The skill's primary function is TTS generation; there are no outbound calls or references to confidential data that would suggest exfiltration.",{"category":108,"check":127,"severity":30,"summary":128},"Hidden Text Tricks","The bundled files do not contain any hidden text tricks, invisible characters, or obfuscated instructions.",{"category":108,"check":130,"severity":30,"summary":131},"Opaque code execution","The skill's implementation is straightforward, calling the `uvx edge-tts` command without any obfuscated code, base64 payloads, or runtime script fetching.",{"category":61,"check":133,"severity":30,"summary":134},"Structural Assumption","The skill assumes the `uvx edge-tts` tool is available and executable, and the output is written to a temporary directory, which are reasonable assumptions for a command-line tool interaction.",{"category":136,"check":137,"severity":45,"summary":138},"Trust","Issues Attention","No issue data is available for this repository.",{"category":140,"check":141,"severity":58,"summary":142},"Versioning","Release Management","There is no manifest version, GitHub release tag, or CHANGELOG. The installation instructions reference `npx skills add aahl/skills`, implying use of the default branch without explicit versioning.",{"category":56,"check":144,"severity":53,"summary":145},"Validation","The skill correctly interpolates parameters into the command line for `uvx edge-tts`. However, there is no explicit validation schema mentioned for inputs like `--text` or `--voice` beyond what the underlying tool might provide.",{"category":108,"check":147,"severity":45,"summary":148},"Unguarded Destructive Operations","The skill's primary operation is generating an audio file, which is not a destructive operation.",{"category":56,"check":150,"severity":30,"summary":151},"Error Handling","The examples imply that the `uvx edge-tts` command will handle errors, and the output is written to a temporary file, suggesting a standard command execution flow that would surface errors appropriately.",{"category":56,"check":153,"severity":45,"summary":154},"Logging","The skill is read-only in terms of its core function (generating audio) and does not perform destructive actions or outbound calls that would necessitate local audit logging.",{"category":156,"check":157,"severity":45,"summary":158},"Compliance","GDPR","The skill processes text for TTS and does not inherently handle personal data. Any personal data within the text is processed by the underlying `uvx edge-tts` tool, which is outside the scope of this skill's direct management.",{"category":156,"check":160,"severity":30,"summary":161},"Target market","The extension functions globally by leveraging a TTS tool and does not exhibit any regional or jurisdictional specific logic. The target market is global.",{"category":61,"check":163,"severity":45,"summary":164},"Runtime stability","The skill relies on a standard command-line tool execution and does not make assumptions about specific editors, shells, or OS features beyond basic POSIX compatibility.",1778054074328,"This skill converts provided text into audio output using Microsoft Edge's neural TTS service via the `uvx edge-tts` command. It supports customization of voices, speed, pitch, and format, and can also generate subtitles. The skill is designed for scenarios where spoken output is preferred over reading, such as for multitasking or accessibility.","2.0.0","3.4.0","The extension is well-documented with clear usage examples and adheres to a single responsibility principle. It leverages an external tool effectively for text-to-speech conversion. The primary areas for improvement are the lack of explicit versioning and the implicit dependency on the `uvx edge-tts` tool without a clear fallback or update mechanism.",85,"A text-to-speech conversion skill using the uvx edge-tts command-line tool.",[15,16,17,18,19,20],"global","verified",{"codeQuality":176,"collectedAt":177,"documentation":178,"maintenance":180,"security":181,"testCoverage":183},{},1778054063232,{"descriptionLength":179,"readmeSize":8},329,{},{"hasNpmPackage":182,"smitheryVerified":182},false,{"hasCi":182,"hasTests":182},{"updatedAt":185},1778054102990,{"githubOwner":187,"githubRepo":188,"locale":24,"slug":19,"type":189},"aahl","skills","skill",true,null,{"extract":193,"llm":196},{"commitSha":194,"license":195},"503806b8502ad5965d31c46b9e46584f0746f33d","MIT-0",{"promptVersionExtension":167,"promptVersionScoring":168,"score":170,"targetMarket":173,"tier":174},{"repoId":198},"kd7f9kgmrb1hqjqtdjzws1v09d865znt",{"_creationTime":200,"_id":198,"identity":201,"providers":203,"workflow":223},1777995558409.888,{"githubOwner":187,"githubRepo":188,"sourceUrl":202},"https://github.com/aahl/skills",{"discover":204,"github":207},{"sources":205},[206],"skills-sh",{"closedIssues90d":8,"forks":208,"homepage":209,"license":210,"openIssues90d":8,"pushedAt":211,"readmeSize":212,"stars":213,"topics":214},13,"https://skills.sh/aahl/skills","MIT",1777948964000,3266,121,[215,216,217,218,219,220,188,221,222],"agent-skills","ai-agents","claude-skills","home-assistant","llm","mcp","feishu","lark",{"discoverAt":224,"extractAt":225,"githubAt":225,"updatedAt":225},1777995558409,1778054062044,{"anyEnrichmentAt":227,"extractAt":228,"githubAt":227,"llmAt":185,"updatedAt":185},1778054061476,1778054061126,[],[231,256,291,315,343,361],{"_creationTime":232,"_id":233,"community":234,"display":235,"identity":243,"providers":245,"relations":250,"workflow":252},1778054691785.2524,"k1712xyy3wyvy83c0f9z7kccg9866jg4",{"reviewCount":8},{"description":236,"installMethods":237,"name":238,"sourceUrl":239,"tags":240},"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",[15,17,16,241,242],"sdk","z-ai-web-dev-sdk",{"githubOwner":244,"githubRepo":215,"locale":24,"slug":15,"type":189},"answerzhao",{"extract":246,"llm":248},{"commitSha":247,"license":210},"aad73edbd0d9ffbc3d6a402b6eafa6dab96d5ebb",{"promptVersionExtension":167,"promptVersionScoring":168,"score":249,"targetMarket":173,"tier":174},95,{"repoId":251},"kd712v2g1pay70swwj0jpv2ggs864zgh",{"anyEnrichmentAt":253,"extractAt":254,"githubAt":253,"llmAt":255,"updatedAt":255},1778054692243,1778054691785,1778054738050,{"_creationTime":257,"_id":258,"community":259,"display":260,"identity":275,"providers":279,"relations":284,"workflow":287},1778053197391.382,"k170wvt5rx3c1hv9a5sfkyezc1866k0q",{"reviewCount":8},{"description":261,"installMethods":262,"name":263,"sourceUrl":264,"tags":265},"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",[15,266,16,267,268,269,270,271,272,273,274],"speech","voice-generation","openai","elevenlabs","bailian","minimax","siliconflow","playht","bun",{"githubOwner":276,"githubRepo":277,"locale":24,"slug":278,"type":189},"iamzhihuix","happy-claude-skills","happy-audio-gen",{"extract":280,"llm":282},{"commitSha":281,"license":210},"f49e7782a551759c9f9e0a4d4417ff053f0a86fd",{"promptVersionExtension":167,"promptVersionScoring":168,"score":283,"targetMarket":173,"tier":174},100,{"parentExtensionId":285,"repoId":286},"k173ydbbp6c0vdpxv5r0q9yvgd867en5","kd7dbbtdq95nkcs3k7fg9w6fdn864j0b",{"anyEnrichmentAt":288,"extractAt":289,"githubAt":288,"llmAt":290,"updatedAt":290},1778053199195,1778053197391,1778053284450,{"_creationTime":292,"_id":293,"community":294,"display":295,"identity":303,"providers":304,"relations":309,"workflow":311},1778053440456.6604,"k17a2cxtswmmk54b8wmpfbp5f9866jr0",{"reviewCount":8},{"description":296,"installMethods":297,"name":298,"sourceUrl":299,"tags":300},"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",[17,269,301,16,302],"voice","synthesis",{"githubOwner":269,"githubRepo":188,"locale":24,"slug":17,"type":189},{"extract":305,"llm":307},{"commitSha":306,"license":210},"b476f0ccf4be0e22b2e77cc39307665425d1472b",{"promptVersionExtension":167,"promptVersionScoring":168,"score":308,"targetMarket":173,"tier":174},98,{"repoId":310},"kd71z3hz1pg97d1k2d6kaqeqtx864knt",{"anyEnrichmentAt":312,"extractAt":313,"githubAt":312,"llmAt":314,"updatedAt":314},1778053440833,1778053440456,1778053480675,{"_creationTime":316,"_id":317,"community":318,"display":319,"identity":329,"providers":332,"relations":337,"workflow":339},1778054035325.8745,"k178gqcwez20sdn3tt9v878bf5866y07",{"reviewCount":8},{"description":320,"installMethods":321,"name":322,"sourceUrl":323,"tags":324},"Generate AI voiceovers, sound effects, and music using ElevenLabs APIs. Use when creating audio content for videos, podcasts, or games. Triggers include generating voiceovers, narration, dialogue, sound effects from descriptions, background music, soundtrack generation, voice cloning, or any audio synthesis task.",{},"ElevenLabs Audio Generation","https://github.com/digitalsamba/claude-code-video-toolkit/tree/HEAD/.claude/skills/elevenlabs",[16,325,15,269,326,327,328],"voiceover","remotion","video","python",{"githubOwner":330,"githubRepo":331,"locale":24,"slug":269,"type":189},"digitalsamba","claude-code-video-toolkit",{"extract":333,"llm":335},{"commitSha":334,"license":210},"dc1bbd251ef137bde9cf460bacb88f13adb3a808",{"promptVersionExtension":167,"promptVersionScoring":168,"score":336,"targetMarket":173,"tier":174},93,{"repoId":338},"kd77w77a4w1f7nnb9v4fmh2eb1865dn1",{"anyEnrichmentAt":340,"extractAt":341,"githubAt":340,"llmAt":342,"updatedAt":342},1778054036248,1778054035325,1778054079849,{"_creationTime":344,"_id":345,"community":346,"display":347,"identity":354,"providers":356,"relations":359,"workflow":360},1778054061126.6428,"k1751e1nss8gew9xpah7s51cah8673h3",{"reviewCount":8},{"description":348,"installMethods":349,"name":350,"sourceUrl":351,"tags":352},"Text-to-speech conversion using GLM-TTS service via the `uvx zai-tts` command for generating audio from text. Use when (1) User requests audio/voice output with the \"tts\" trigger or keyword. (2) Content needs to be spoken rather than read (multitasking, accessibility, podcast, driving, cooking). (3) Using pre-cloned voices for speech.",{},"Zai-TTS","https://github.com/aahl/skills/tree/HEAD/skills/zai-tts",[15,16,353,18],"glm-tts",{"githubOwner":187,"githubRepo":188,"locale":24,"slug":355,"type":189},"zai-tts",{"extract":357,"llm":358},{"commitSha":194,"license":210},{"promptVersionExtension":167,"promptVersionScoring":168,"score":170,"targetMarket":173,"tier":174},{"repoId":198},{"anyEnrichmentAt":227,"extractAt":228,"githubAt":227,"llmAt":185,"updatedAt":185},{"_creationTime":362,"_id":363,"community":364,"display":365,"identity":374,"providers":377,"relations":381,"workflow":383},1778054291668.0964,"k17477k0d5jgrwmqqkgp1phgen866eck",{"reviewCount":8},{"description":366,"installMethods":367,"name":368,"sourceUrl":369,"tags":370},"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",[15,266,301,371,372,373],"emotion","companion","script",{"githubOwner":375,"githubRepo":188,"locale":24,"slug":376,"type":189},"noizai","characteristic-voice",{"extract":378,"llm":380},{"commitSha":379,"license":45},"3428725f8c34e2179e0bdaf4c441697e0014d289",{"promptVersionExtension":167,"promptVersionScoring":168,"score":308,"targetMarket":173,"tier":174},{"repoId":382},"kd76a0e9dvgjrpvm0qe8k24qy18653ah",{"anyEnrichmentAt":384,"extractAt":385,"githubAt":384,"llmAt":386,"updatedAt":386},1778054291966,1778054291668,1778054322837]