# Send ElevenLabs Voices to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "elevenlabs-voices", "name": "ElevenLabs Voices", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/robbyczgw-cla/elevenlabs-voices", "canonicalUrl": "https://clawhub.ai/robbyczgw-cla/elevenlabs-voices", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/elevenlabs-voices", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=elevenlabs-voices", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "CHANGELOG.md", "README.md", "SKILL.md", "examples.md", "package.json", "pronunciations.json" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "elevenlabs-voices", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-02T21:03:00.707Z", "expiresAt": "2026-05-09T21:03:00.707Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=elevenlabs-voices", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=elevenlabs-voices", "contentDisposition": "attachment; filename=\"elevenlabs-voices-2.1.6.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "elevenlabs-voices" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/elevenlabs-voices" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/elevenlabs-voices", "downloadUrl": "https://openagent3.xyz/downloads/elevenlabs-voices", "agentUrl": "https://openagent3.xyz/skills/elevenlabs-voices/agent", "manifestUrl": "https://openagent3.xyz/skills/elevenlabs-voices/agent.json", "briefUrl": "https://openagent3.xyz/skills/elevenlabs-voices/agent.md" } } ``` ## Documentation ### ElevenLabs Voice Personas v2.1 Comprehensive voice synthesis toolkit using ElevenLabs API. ### 🚀 First Run - Setup Wizard When you first use this skill (no config.json exists), run the interactive setup wizard: python3 scripts/setup.py The wizard will guide you through: API Key - Enter your ElevenLabs API key (required) Default Voice - Choose from popular voices (Rachel, Adam, Bella, etc.) Language - Set your preferred language (32 supported) Audio Quality - Standard or high quality output Cost Tracking - Enable usage and cost monitoring Budget Limit - Optional monthly spending cap 🔒 Privacy: Your API key is stored locally in config.json only. It never leaves your machine and is automatically excluded from git via .gitignore. To reconfigure at any time, simply run the setup wizard again. ### ✨ Features 18 Voice Personas - Carefully curated voices for different use cases 32 Languages - Multi-language synthesis with the multilingual v2 model Streaming Mode - Real-time audio output as it generates Sound Effects (SFX) - AI-generated sound effects from text prompts Batch Processing - Process multiple texts in one go Cost Tracking - Monitor character usage and estimated costs Voice Design - Create custom voices from descriptions Pronunciation Dictionary - Custom word pronunciation rules OpenClaw Integration - Works with OpenClaw's built-in TTS ### 🎙 Available Voices VoiceAccentGenderPersonaBest Forrachel🇺🇸 USfemalewarmConversations, tutorialsadam🇺🇸 USmalenarratorDocumentaries, audiobooksbella🇺🇸 USfemaleprofessionalBusiness, presentationsbrian🇺🇸 USmalecomfortingMeditation, calm contentgeorge🇬🇧 UKmalestorytellerAudiobooks, storytellingalice🇬🇧 UKfemaleeducatorTutorials, explanationscallum🇺🇸 USmaletricksterPlayful, gamingcharlie🇦🇺 AUmaleenergeticSports, motivationjessica🇺🇸 USfemaleplayfulSocial media, casuallily🇬🇧 UKfemaleactressDrama, elegant contentmatilda🇺🇸 USfemaleprofessionalCorporate, newsriver🇺🇸 USneutralneutralInclusive, informativeroger🇺🇸 USmalecasualPodcasts, relaxeddaniel🇬🇧 UKmalebroadcasterNews, announcementseric🇺🇸 USmaletrustworthyBusiness, corporatechris🇺🇸 USmalefriendlyTutorials, approachablewill🇺🇸 USmaleoptimistMotivation, upliftingliam🇺🇸 USmalesocialYouTube, social media ### 🎯 Quick Presets default → rachel (warm, friendly) narrator → adam (documentaries) professional → matilda (corporate) storyteller → george (audiobooks) educator → alice (tutorials) calm → brian (meditation) energetic → liam (social media) trustworthy → eric (business) neutral → river (inclusive) british → george australian → charlie broadcaster → daniel (news) ### 🌍 Supported Languages (32) The multilingual v2 model supports these languages: CodeLanguageCodeLanguageenEnglishplPolishdeGermannlDutchesSpanishsvSwedishfrFrenchdaDanishitItalianfiFinnishptPortuguesenoNorwegianruRussiantrTurkishukUkrainiancsCzechjaJapaneseskSlovakkoKoreanhuHungarianzhChineseroRomanianarArabicbgBulgarianhiHindihrCroatiantaTamilelGreekidIndonesianmsMalayviVietnamesethThai # Synthesize in German python3 tts.py --text "Guten Tag!" --voice rachel --lang de # Synthesize in French python3 tts.py --text "Bonjour le monde!" --voice adam --lang fr # List all languages python3 tts.py --languages ### Basic Text-to-Speech # List all voices python3 scripts/tts.py --list # Generate speech python3 scripts/tts.py --text "Hello world" --voice rachel --output hello.mp3 # Use a preset python3 scripts/tts.py --text "Breaking news..." --voice broadcaster --output news.mp3 # Multi-language python3 scripts/tts.py --text "Bonjour!" --voice rachel --lang fr --output french.mp3 ### Streaming Mode Generate audio with real-time streaming (good for long texts): # Stream audio as it generates python3 scripts/tts.py --text "This is a long story..." --voice adam --stream # Streaming with custom output python3 scripts/tts.py --text "Chapter one..." --voice george --stream --output chapter1.mp3 ### Batch Processing Process multiple texts from a file: # From newline-separated text file python3 scripts/tts.py --batch texts.txt --voice rachel --output-dir ./audio # From JSON file python3 scripts/tts.py --batch batch.json --output-dir ./output JSON batch format: [ {"text": "First line", "voice": "rachel", "output": "line1.mp3"}, {"text": "Second line", "voice": "adam", "output": "line2.mp3"}, {"text": "Third line"} ] Simple text format (one per line): Hello, this is the first sentence. This is the second sentence. And this is the third. ### Usage Statistics # Show usage stats and cost estimates python3 scripts/tts.py --stats # Reset statistics python3 scripts/tts.py --reset-stats ### 🎵 Sound Effects (SFX) Generate AI-powered sound effects from text descriptions: # Generate a sound effect python3 scripts/sfx.py --prompt "Thunder rumbling in the distance" # With specific duration (0.5-22 seconds) python3 scripts/sfx.py --prompt "Cat meowing" --duration 3 --output cat.mp3 # Adjust prompt influence (0.0-1.0) python3 scripts/sfx.py --prompt "Footsteps on gravel" --influence 0.5 # Batch SFX generation python3 scripts/sfx.py --batch sounds.json --output-dir ./sfx # Show prompt examples python3 scripts/sfx.py --examples Example prompts: "Thunder rumbling in the distance" "Cat purring contentedly" "Typing on a mechanical keyboard" "Spaceship engine humming" "Coffee shop background chatter" ### 🎨 Voice Design Create custom voices from text descriptions: # Basic voice design python3 scripts/voice-design.py --gender female --age middle_aged --accent american \\ --description "A warm, motherly voice" # With custom preview text python3 scripts/voice-design.py --gender male --age young --accent british \\ --text "Welcome to the adventure!" --output preview.mp3 # Save to your ElevenLabs library python3 scripts/voice-design.py --gender female --age young --accent american \\ --description "Energetic podcast host" --save "MyHost" # List all design options python3 scripts/voice-design.py --options Voice Design Options: OptionValuesGendermale, female, neutralAgeyoung, middle_aged, oldAccentamerican, british, african, australian, indian, latin, middle_eastern, scandinavian, eastern_europeanAccent Strength0.3-2.0 (subtle to strong) ### 📖 Pronunciation Dictionary Customize how words are pronounced: Edit pronunciations.json: { "rules": [ { "word": "OpenClaw", "replacement": "Open Claw", "comment": "Pronounce as two words" }, { "word": "API", "replacement": "A P I", "comment": "Spell out acronym" } ] } Usage: # Pronunciations are applied automatically python3 scripts/tts.py --text "The OpenClaw API is great" --voice rachel # Disable pronunciations python3 scripts/tts.py --text "The API is great" --voice rachel --no-pronunciations ### 💰 Cost Tracking The skill tracks your character usage and estimates costs: python3 scripts/tts.py --stats Output: 📊 ElevenLabs Usage Statistics Total Characters: 15,230 Total Requests: 42 Since: 2024-01-15 💰 Estimated Costs: Starter $4.57 ($0.30/1k chars) Creator $3.66 ($0.24/1k chars) Pro $2.74 ($0.18/1k chars) Scale $1.68 ($0.11/1k chars) ### Using with OpenClaw's Built-in TTS OpenClaw has built-in TTS support that can use ElevenLabs. Configure in ~/.openclaw/openclaw.json: { "tts": { "enabled": true, "provider": "elevenlabs", "elevenlabs": { "apiKey": "your-api-key-here", "voice": "rachel", "model": "eleven_multilingual_v2" } } } ### Triggering TTS in Chat In OpenClaw conversations: Use /tts on to enable automatic TTS Use the tts tool directly for one-off speech Request "read this aloud" or "speak this" ### Using Skill Scripts from OpenClaw # OpenClaw can run these scripts directly exec python3 /path/to/skills/elevenlabs-voices/scripts/tts.py --text "Hello" --voice rachel ### ⚙ Configuration The scripts look for API key in this order: ELEVEN_API_KEY or ELEVENLABS_API_KEY environment variable Skill-local .env file (in the skill directory) Create .env file: echo 'ELEVEN_API_KEY=your-key-here' > .env Note: The skill no longer reads from ~/.openclaw/openclaw.json. Use environment variables or the skill-local .env file. ### 🎛 Voice Settings Each voice has tuned settings for optimal output: SettingRangeDescriptionstability0.0-1.0Higher = consistent, lower = expressivesimilarity_boost0.0-1.0How closely to match original voicestyle0.0-1.0Exaggeration of speaking style ### 📝 Triggers "use {voice_name} voice" "speak as {persona}" "list voices" "voice settings" "generate sound effect" "design a voice" ### 📁 Files elevenlabs-voices/ ├── SKILL.md # This documentation ├── README.md # Quick start guide ├── config.json # Your local config (created by setup, in .gitignore) ├── voices.json # Voice definitions & settings ├── pronunciations.json # Custom pronunciation rules ├── examples.md # Detailed usage examples ├── scripts/ │ ├── setup.py # Interactive setup wizard │ ├── tts.py # Main TTS script │ ├── sfx.py # Sound effects generator │ └── voice-design.py # Voice design tool └── references/ └── voice-guide.md # Voice selection guide ### 🔗 Links ElevenLabs API Documentation Voice Library Sound Effects API Voice Design API ### v2.1.0 Added interactive setup wizard (scripts/setup.py) Onboarding guides through API key, voice, language, quality, and budget settings Config stored locally in config.json (added to .gitignore) Professional, privacy-focused setup experience ### v2.0.0 Added 32 language support with --lang parameter Added streaming mode with --stream flag Added sound effects generation (sfx.py) Added batch processing with --batch flag Added cost tracking with --stats flag Added voice design tool (voice-design.py) Added pronunciation dictionary support Added OpenClaw TTS integration documentation Improved error handling and progress output ## Trust - Source: tencent - Verification: Indexed source record - Publisher: robbyczgw-cla - Version: 2.1.6 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-02T21:03:00.707Z - Expires at: 2026-05-09T21:03:00.707Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/elevenlabs-voices) - [Send to Agent page](https://openagent3.xyz/skills/elevenlabs-voices/agent) - [JSON manifest](https://openagent3.xyz/skills/elevenlabs-voices/agent.json) - [Markdown brief](https://openagent3.xyz/skills/elevenlabs-voices/agent.md) - [Download page](https://openagent3.xyz/downloads/elevenlabs-voices)