{
  "schemaVersion": "1.0",
  "item": {
    "slug": "elevenlabs-tts",
    "name": "Elevenlabs Tts",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/Shaharsha/elevenlabs-tts",
    "canonicalUrl": "https://clawhub.ai/Shaharsha/elevenlabs-tts",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/elevenlabs-tts",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=elevenlabs-tts",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/audio-tags.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "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."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "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. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/elevenlabs-tts"
    },
    "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."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/elevenlabs-tts",
    "agentPageUrl": "https://openagent3.xyz/skills/elevenlabs-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/elevenlabs-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/elevenlabs-tts/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "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."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "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. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "ElevenLabs TTS (Text-to-Speech)",
        "body": "Generate expressive voice messages using ElevenLabs v3 with audio tags."
      },
      {
        "title": "Prerequisites",
        "body": "ElevenLabs API Key (ELEVENLABS_API_KEY): Required. Get one at elevenlabs.io → Profile → API Keys. Configure in openclaw.json under messages.tts.elevenlabs.apiKey.\nffmpeg: Required for audio format conversion (MP3 → Opus for WhatsApp compatibility). Must be installed and available on PATH."
      },
      {
        "title": "Quick Start Examples",
        "body": "Storytelling (emotional journey):\n\n[soft] It started like any other day... [pause] But something felt different. [nervous] My hands were shaking as I opened the envelope. [gasps] I got in! [excited] I actually got in! [laughs] [happy] This changes everything!\n\nHorror/Suspense (building dread):\n\n[whispers] The house has been empty for years... [pause] At least, that's what they told me. [nervous] But I keep hearing footsteps. [scared] They're getting closer. [gasps] [panicking] The door— it's opening by itself!\n\nConversation with reactions:\n\n[curious] So what happened at the meeting? [pause] [surprised] Wait, they fired him?! [gasps] [sad] That's terrible... [sighs] He had a family. [thoughtful] I wonder what he'll do now.\n\nHebrew (romantic moment):\n\n[soft] היא עמדה שם, מול השקיעה... [pause] הלב שלי פעם כל כך חזק. [nervous] לא ידעתי מה להגיד. [hesitates] אני... [breathes] [tender] את יודעת שאני אוהב אותך, נכון?\n\nSpanish (celebration to reflection):\n\n[excited] ¡Lo logramos! [laughs] [happy] No puedo creerlo... [pause] [thoughtful] Fueron tantos años de trabajo. [emotional] [soft] Gracias a todos los que creyeron en mí. [sighs] [content] Valió la pena cada momento."
      },
      {
        "title": "Configuration (OpenClaw)",
        "body": "In openclaw.json, configure TTS under messages.tts:\n\n{\n  \"messages\": {\n    \"tts\": {\n      \"provider\": \"elevenlabs\",\n      \"elevenlabs\": {\n        \"apiKey\": \"sk_your_api_key_here\",\n        \"voiceId\": \"pNInz6obpgDQGcFmaJgB\",\n        \"modelId\": \"eleven_v3\",\n        \"languageCode\": \"en\",\n        \"voiceSettings\": {\n          \"stability\": 0.5,\n          \"similarityBoost\": 0.75,\n          \"style\": 0,\n          \"useSpeakerBoost\": true,\n          \"speed\": 1\n        }\n      }\n    }\n  }\n}\n\nGetting your API Key:\n\nGo to https://elevenlabs.io\nSign up/login\nClick profile → API Keys\nCopy your key"
      },
      {
        "title": "Recommended Voices for v3",
        "body": "These premade voices are optimized for v3 and work well with audio tags:\n\nVoiceIDGenderAccentBest ForAdampNInz6obpgDQGcFmaJgBMaleAmericanDeep narration, general useRachel21m00Tcm4TlvDq8ikWAMFemaleAmericanCalm narration, conversationalBriannPczCjzI2devNBz1zQrbMaleAmericanDeep narration, podcastsCharlotteXB0fDUnXU5powFXDhCwaFemaleEnglish-SwedishExpressive, video gamesGeorgeJBFqnCBsd6RMkjVDRZzbMaleBritishRaspy narration, storytelling\n\nFinding more voices:\n\nBrowse: https://elevenlabs.io/voice-library\nv3-optimized collection: https://elevenlabs.io/app/voice-library/collections/aF6JALq9R6tXwCczjhKH\nAPI: GET https://api.elevenlabs.io/v1/voices\n\nVoice selection tips:\n\nUse IVC (Instant Voice Clone) or premade voices - PVC not optimized for v3 yet\nMatch voice character to your use case (whispering voice won't shout well)\nFor expressive IVCs, include varied emotional tones in training samples"
      },
      {
        "title": "Model Settings",
        "body": "Model: eleven_v3 (alpha) - ONLY model supporting audio tags\nLanguages: 70+ supported with full audio tag control"
      },
      {
        "title": "Stability Modes",
        "body": "ModeStabilityDescriptionCreative0.3-0.5More emotional/expressive, may hallucinateNatural0.5-0.7Balanced, closest to original voiceRobust0.7-1.0Highly stable, less responsive to tags\n\nFor audio tags, use Creative (0.5) or Natural. Higher stability reduces tag responsiveness."
      },
      {
        "title": "Speed Control",
        "body": "Range: 0.7 (slow) to 1.2 (fast), default 1.0\n\nExtreme values affect quality. For pacing, prefer audio tags like [rushed] or [drawn out]."
      },
      {
        "title": "Length Limits",
        "body": "Optimal: <800 characters per segment (best quality)\nMaximum: 10,000 characters (API hard limit)\nQuality degrades with longer text - voice becomes inconsistent"
      },
      {
        "title": "Audio Tags - Best Practices for Natural Sound",
        "body": "How many tags to use:\n\n1-2 tags per sentence or phrase (not more!)\nTags persist until the next tag - no need to repeat\nOverusing tags sounds unnatural and robotic\n\nWhere to place tags:\n\nAt emotional transition points\nBefore key dramatic moments\nWhen energy/pace changes\n\nContext matters:\n\nWrite text that matches the tag emotion\nLonger text with context = better interpretation\nExample: [nervous] I... I'm not sure about this. What if it doesn't work? works better than [nervous] Hello.\n\nCombine tags for nuance:\n\n[nervously][whispers] = nervous whispering\n[excited][laughs] = excited laughter\nKeep combinations to 2 tags max\n\nRegenerate for best results:\n\nv3 is non-deterministic - same text = different outputs\nGenerate 3+ versions, pick the best\nSmall text tweaks can improve results\n\nMatch tag to voice:\n\nDon't use [shouts] on a whispering voice\nDon't use [whispers] on a loud/energetic voice\nTest tags with your chosen voice"
      },
      {
        "title": "SSML Not Supported",
        "body": "v3 does NOT support SSML break tags. Use audio tags and punctuation instead."
      },
      {
        "title": "Punctuation Effects (use with tags!)",
        "body": "Punctuation enhances audio tags:\n\nEllipses (...) → dramatic pauses: [nervous] I... I don't know...\nCAPS → emphasis: [excited] That's AMAZING!\nDashes (—) → interruptions: [explaining] So what you do is— [interrupting] Wait!\nQuestion marks → uncertainty: [nervous] Are you sure about this?\nExclamation! → energy boost: [happy] We did it!\n\nCombine tags + punctuation for maximum effect:\n\n[tired] It was a long day... [sighs] Nobody listens anymore."
      },
      {
        "title": "Complete Workflow",
        "body": "Generate with tts tool (returns MP3)\nConvert to Opus (required for Android!)\nSend with message tool"
      },
      {
        "title": "Step-by-Step",
        "body": "1. Generate TTS (add [pause] at end to prevent cutoff):\n\ntts text=\"[excited] This is amazing! [pause]\" channel=whatsapp\n\nReturns: MEDIA:/tmp/tts-xxx/voice-123.mp3\n\n2. Convert MP3 → Opus:\n\nffmpeg -i /tmp/tts-xxx/voice-123.mp3 -c:a libopus -b:a 64k -vbr on -application voip /tmp/tts-xxx/voice-123.ogg\n\n3. Send the Opus file:\n\nNote: The message field below contains a Unicode Left-to-Right Mark (U+200E) between the quotes.\nThis is intentional — WhatsApp requires a non-empty message body to send voice notes.\nThe LTR mark is invisible but satisfies this requirement without displaying any text.\n\nmessage action=send channel=whatsapp target=\"+972...\" filePath=\"/tmp/tts-xxx/voice-123.ogg\" asVoice=true message=\"‎\""
      },
      {
        "title": "Why Opus?",
        "body": "FormatiOSAndroidTranscribeMP3✅ Works❌ May fail❌ NoOpus (.ogg)✅ Works✅ Works✅ Yes\n\nAlways convert to Opus - it's the only format that:\n\nWorks on all devices (iOS + Android)\nSupports WhatsApp's transcribe button"
      },
      {
        "title": "Audio Cutoff Fix",
        "body": "ElevenLabs sometimes cuts off the last word. Always add [pause] or ... at the end:\n\n[excited] This is amazing! [pause]"
      },
      {
        "title": "Long-Form Audio (Podcasts)",
        "body": "For content >800 chars:\n\nSplit into short segments (<800 chars each)\nGenerate each with tts tool\nConcatenate with ffmpeg:\ncat > list.txt << EOF\nfile '/path/file1.mp3'\nfile '/path/file2.mp3'\nEOF\nffmpeg -f concat -safe 0 -i list.txt -c copy final.mp3\n\n\nConvert to Opus for WhatsApp\nSend as single voice message\n\nImportant: Don't mention \"part 2\" or \"chapter\" - keep it seamless."
      },
      {
        "title": "Multi-Speaker Dialogue",
        "body": "v3 can handle multiple characters in one generation:\n\nJessica: [whispers] Did you hear that?\nChris: [interrupting] —I heard it too!\nJessica: [panicking] We need to hide!\n\nDialogue tags: [interrupting], [overlapping], [cuts in], [interjecting]"
      },
      {
        "title": "Audio Tags Quick Reference",
        "body": "CategoryTagsWhen to UseEmotions[excited], [happy], [sad], [angry], [nervous], [curious]Main emotional state - use 1 per sectionDelivery[whispers], [shouts], [soft], [rushed], [drawn out]Volume/speed changesReactions[laughs], [sighs], [gasps], [clears throat], [gulps]Natural human moments - sprinkle sparinglyPacing[pause], [hesitates], [stammers], [breathes]Dramatic timingCharacter[French accent], [British accent], [robotic tone]Character voice shiftsDialogue[interrupting], [overlapping], [cuts in]Multi-speaker conversations\n\nMost effective tags (reliable results):\n\nEmotions: [excited], [nervous], [sad], [happy]\nReactions: [laughs], [sighs], [whispers]\nPacing: [pause]\n\nLess reliable (test and regenerate):\n\nSound effects: [explosion], [gunshot]\nAccents: results vary by voice\n\nFull tag list: See references/audio-tags.md"
      },
      {
        "title": "Troubleshooting",
        "body": "Tags read aloud?\n\nVerify using eleven_v3 model\nUse IVC/premade voices, not PVC\nSimplify tags (no \"tone\" suffix)\nIncrease text length (250+ chars)\n\nVoice inconsistent?\n\nSegment is too long - split at <800 chars\nRegenerate (v3 is non-deterministic)\nTry lower stability setting\n\nWhatsApp won't play?\n\nConvert to Opus format (see above)\n\nNo emotion despite tags?\n\nVoice may not match tag style\nTry Creative stability mode (0.5)\nAdd more context around the tag"
      }
    ],
    "body": "ElevenLabs TTS (Text-to-Speech)\n\nGenerate expressive voice messages using ElevenLabs v3 with audio tags.\n\nPrerequisites\nElevenLabs API Key (ELEVENLABS_API_KEY): Required. Get one at elevenlabs.io → Profile → API Keys. Configure in openclaw.json under messages.tts.elevenlabs.apiKey.\nffmpeg: Required for audio format conversion (MP3 → Opus for WhatsApp compatibility). Must be installed and available on PATH.\nQuick Start Examples\n\nStorytelling (emotional journey):\n\n[soft] It started like any other day... [pause] But something felt different. [nervous] My hands were shaking as I opened the envelope. [gasps] I got in! [excited] I actually got in! [laughs] [happy] This changes everything!\n\n\nHorror/Suspense (building dread):\n\n[whispers] The house has been empty for years... [pause] At least, that's what they told me. [nervous] But I keep hearing footsteps. [scared] They're getting closer. [gasps] [panicking] The door— it's opening by itself!\n\n\nConversation with reactions:\n\n[curious] So what happened at the meeting? [pause] [surprised] Wait, they fired him?! [gasps] [sad] That's terrible... [sighs] He had a family. [thoughtful] I wonder what he'll do now.\n\n\nHebrew (romantic moment):\n\n[soft] היא עמדה שם, מול השקיעה... [pause] הלב שלי פעם כל כך חזק. [nervous] לא ידעתי מה להגיד. [hesitates] אני... [breathes] [tender] את יודעת שאני אוהב אותך, נכון?\n\n\nSpanish (celebration to reflection):\n\n[excited] ¡Lo logramos! [laughs] [happy] No puedo creerlo... [pause] [thoughtful] Fueron tantos años de trabajo. [emotional] [soft] Gracias a todos los que creyeron en mí. [sighs] [content] Valió la pena cada momento.\n\nConfiguration (OpenClaw)\n\nIn openclaw.json, configure TTS under messages.tts:\n\n{\n  \"messages\": {\n    \"tts\": {\n      \"provider\": \"elevenlabs\",\n      \"elevenlabs\": {\n        \"apiKey\": \"sk_your_api_key_here\",\n        \"voiceId\": \"pNInz6obpgDQGcFmaJgB\",\n        \"modelId\": \"eleven_v3\",\n        \"languageCode\": \"en\",\n        \"voiceSettings\": {\n          \"stability\": 0.5,\n          \"similarityBoost\": 0.75,\n          \"style\": 0,\n          \"useSpeakerBoost\": true,\n          \"speed\": 1\n        }\n      }\n    }\n  }\n}\n\n\nGetting your API Key:\n\nGo to https://elevenlabs.io\nSign up/login\nClick profile → API Keys\nCopy your key\nRecommended Voices for v3\n\nThese premade voices are optimized for v3 and work well with audio tags:\n\nVoice\tID\tGender\tAccent\tBest For\nAdam\tpNInz6obpgDQGcFmaJgB\tMale\tAmerican\tDeep narration, general use\nRachel\t21m00Tcm4TlvDq8ikWAM\tFemale\tAmerican\tCalm narration, conversational\nBrian\tnPczCjzI2devNBz1zQrb\tMale\tAmerican\tDeep narration, podcasts\nCharlotte\tXB0fDUnXU5powFXDhCwa\tFemale\tEnglish-Swedish\tExpressive, video games\nGeorge\tJBFqnCBsd6RMkjVDRZzb\tMale\tBritish\tRaspy narration, storytelling\n\nFinding more voices:\n\nBrowse: https://elevenlabs.io/voice-library\nv3-optimized collection: https://elevenlabs.io/app/voice-library/collections/aF6JALq9R6tXwCczjhKH\nAPI: GET https://api.elevenlabs.io/v1/voices\n\nVoice selection tips:\n\nUse IVC (Instant Voice Clone) or premade voices - PVC not optimized for v3 yet\nMatch voice character to your use case (whispering voice won't shout well)\nFor expressive IVCs, include varied emotional tones in training samples\nModel Settings\nModel: eleven_v3 (alpha) - ONLY model supporting audio tags\nLanguages: 70+ supported with full audio tag control\nStability Modes\nMode\tStability\tDescription\nCreative\t0.3-0.5\tMore emotional/expressive, may hallucinate\nNatural\t0.5-0.7\tBalanced, closest to original voice\nRobust\t0.7-1.0\tHighly stable, less responsive to tags\n\nFor audio tags, use Creative (0.5) or Natural. Higher stability reduces tag responsiveness.\n\nSpeed Control\n\nRange: 0.7 (slow) to 1.2 (fast), default 1.0\n\nExtreme values affect quality. For pacing, prefer audio tags like [rushed] or [drawn out].\n\nCritical Rules\nLength Limits\nOptimal: <800 characters per segment (best quality)\nMaximum: 10,000 characters (API hard limit)\nQuality degrades with longer text - voice becomes inconsistent\nAudio Tags - Best Practices for Natural Sound\n\nHow many tags to use:\n\n1-2 tags per sentence or phrase (not more!)\nTags persist until the next tag - no need to repeat\nOverusing tags sounds unnatural and robotic\n\nWhere to place tags:\n\nAt emotional transition points\nBefore key dramatic moments\nWhen energy/pace changes\n\nContext matters:\n\nWrite text that matches the tag emotion\nLonger text with context = better interpretation\nExample: [nervous] I... I'm not sure about this. What if it doesn't work? works better than [nervous] Hello.\n\nCombine tags for nuance:\n\n[nervously][whispers] = nervous whispering\n[excited][laughs] = excited laughter\nKeep combinations to 2 tags max\n\nRegenerate for best results:\n\nv3 is non-deterministic - same text = different outputs\nGenerate 3+ versions, pick the best\nSmall text tweaks can improve results\n\nMatch tag to voice:\n\nDon't use [shouts] on a whispering voice\nDon't use [whispers] on a loud/energetic voice\nTest tags with your chosen voice\nSSML Not Supported\n\nv3 does NOT support SSML break tags. Use audio tags and punctuation instead.\n\nPunctuation Effects (use with tags!)\n\nPunctuation enhances audio tags:\n\nEllipses (...) → dramatic pauses: [nervous] I... I don't know...\nCAPS → emphasis: [excited] That's AMAZING!\nDashes (—) → interruptions: [explaining] So what you do is— [interrupting] Wait!\nQuestion marks → uncertainty: [nervous] Are you sure about this?\nExclamation! → energy boost: [happy] We did it!\n\nCombine tags + punctuation for maximum effect:\n\n[tired] It was a long day... [sighs] Nobody listens anymore.\n\nWhatsApp Voice Messages\nComplete Workflow\nGenerate with tts tool (returns MP3)\nConvert to Opus (required for Android!)\nSend with message tool\nStep-by-Step\n\n1. Generate TTS (add [pause] at end to prevent cutoff):\n\ntts text=\"[excited] This is amazing! [pause]\" channel=whatsapp\n\n\nReturns: MEDIA:/tmp/tts-xxx/voice-123.mp3\n\n2. Convert MP3 → Opus:\n\nffmpeg -i /tmp/tts-xxx/voice-123.mp3 -c:a libopus -b:a 64k -vbr on -application voip /tmp/tts-xxx/voice-123.ogg\n\n\n3. Send the Opus file:\n\nNote: The message field below contains a Unicode Left-to-Right Mark (U+200E) between the quotes. This is intentional — WhatsApp requires a non-empty message body to send voice notes. The LTR mark is invisible but satisfies this requirement without displaying any text.\n\nmessage action=send channel=whatsapp target=\"+972...\" filePath=\"/tmp/tts-xxx/voice-123.ogg\" asVoice=true message=\"‎\"\n\nWhy Opus?\nFormat\tiOS\tAndroid\tTranscribe\nMP3\t✅ Works\t❌ May fail\t❌ No\nOpus (.ogg)\t✅ Works\t✅ Works\t✅ Yes\n\nAlways convert to Opus - it's the only format that:\n\nWorks on all devices (iOS + Android)\nSupports WhatsApp's transcribe button\nAudio Cutoff Fix\n\nElevenLabs sometimes cuts off the last word. Always add [pause] or ... at the end:\n\n[excited] This is amazing! [pause]\n\nLong-Form Audio (Podcasts)\n\nFor content >800 chars:\n\nSplit into short segments (<800 chars each)\nGenerate each with tts tool\nConcatenate with ffmpeg:\ncat > list.txt << EOF\nfile '/path/file1.mp3'\nfile '/path/file2.mp3'\nEOF\nffmpeg -f concat -safe 0 -i list.txt -c copy final.mp3\n\nConvert to Opus for WhatsApp\nSend as single voice message\n\nImportant: Don't mention \"part 2\" or \"chapter\" - keep it seamless.\n\nMulti-Speaker Dialogue\n\nv3 can handle multiple characters in one generation:\n\nJessica: [whispers] Did you hear that?\nChris: [interrupting] —I heard it too!\nJessica: [panicking] We need to hide!\n\n\nDialogue tags: [interrupting], [overlapping], [cuts in], [interjecting]\n\nAudio Tags Quick Reference\nCategory\tTags\tWhen to Use\nEmotions\t[excited], [happy], [sad], [angry], [nervous], [curious]\tMain emotional state - use 1 per section\nDelivery\t[whispers], [shouts], [soft], [rushed], [drawn out]\tVolume/speed changes\nReactions\t[laughs], [sighs], [gasps], [clears throat], [gulps]\tNatural human moments - sprinkle sparingly\nPacing\t[pause], [hesitates], [stammers], [breathes]\tDramatic timing\nCharacter\t[French accent], [British accent], [robotic tone]\tCharacter voice shifts\nDialogue\t[interrupting], [overlapping], [cuts in]\tMulti-speaker conversations\n\nMost effective tags (reliable results):\n\nEmotions: [excited], [nervous], [sad], [happy]\nReactions: [laughs], [sighs], [whispers]\nPacing: [pause]\n\nLess reliable (test and regenerate):\n\nSound effects: [explosion], [gunshot]\nAccents: results vary by voice\n\nFull tag list: See references/audio-tags.md\n\nTroubleshooting\n\nTags read aloud?\n\nVerify using eleven_v3 model\nUse IVC/premade voices, not PVC\nSimplify tags (no \"tone\" suffix)\nIncrease text length (250+ chars)\n\nVoice inconsistent?\n\nSegment is too long - split at <800 chars\nRegenerate (v3 is non-deterministic)\nTry lower stability setting\n\nWhatsApp won't play?\n\nConvert to Opus format (see above)\n\nNo emotion despite tags?\n\nVoice may not match tag style\nTry Creative stability mode (0.5)\nAdd more context around the tag"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/Shaharsha/elevenlabs-tts",
    "publisherUrl": "https://clawhub.ai/Shaharsha/elevenlabs-tts",
    "owner": "Shaharsha",
    "version": "2.2.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/elevenlabs-tts",
    "downloadUrl": "https://openagent3.xyz/downloads/elevenlabs-tts",
    "agentUrl": "https://openagent3.xyz/skills/elevenlabs-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/elevenlabs-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/elevenlabs-tts/agent.md"
  }
}