{ "schemaVersion": "1.0", "item": { "slug": "text-to-speech", "name": "Text To Speech", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/okaris/text-to-speech", "canonicalUrl": "https://clawhub.ai/okaris/text-to-speech", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/text-to-speech", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=text-to-speech", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "SKILL.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": "2026-05-07T17:22:31.273Z", "expiresAt": "2026-05-14T17:22:31.273Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report", "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.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/text-to-speech" }, "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/text-to-speech", "agentPageUrl": "https://openagent3.xyz/skills/text-to-speech/agent", "manifestUrl": "https://openagent3.xyz/skills/text-to-speech/agent.json", "briefUrl": "https://openagent3.xyz/skills/text-to-speech/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": "Text-to-Speech", "body": "Convert text to natural speech via inference.sh CLI." }, { "title": "Quick Start", "body": "# Install CLI\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate speech\ninfsh app run infsh/kokoro-tts --input '{\"text\": \"Hello, welcome to our product demo.\"}'\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available." }, { "title": "Available Models", "body": "ModelApp IDBest ForDIA TTSinfsh/dia-ttsConversational, expressiveKokoro TTSinfsh/kokoro-ttsFast, naturalChatterboxinfsh/chatterboxGeneral purposeHiggs Audioinfsh/higgs-audioEmotional controlVibeVoiceinfsh/vibevoicePodcasts, long-form" }, { "title": "Browse All Audio Apps", "body": "infsh app list --category audio" }, { "title": "Basic Text-to-Speech", "body": "infsh app run infsh/kokoro-tts --input '{\"text\": \"Welcome to our tutorial.\"}'" }, { "title": "Conversational TTS with DIA", "body": "infsh app sample infsh/dia-tts --save input.json\n\n# Edit input.json:\n# {\n# \"text\": \"Hey! How are you doing today? I'm really excited to share this with you.\",\n# \"voice\": \"conversational\"\n# }\n\ninfsh app run infsh/dia-tts --input input.json" }, { "title": "Long-form Audio (Podcasts)", "body": "infsh app sample infsh/vibevoice --save input.json\n\n# Edit input.json with your podcast script\ninfsh app run infsh/vibevoice --input input.json" }, { "title": "Expressive Speech with Higgs", "body": "infsh app sample infsh/higgs-audio --save input.json\n\n# {\n# \"text\": \"This is absolutely incredible!\",\n# \"emotion\": \"excited\"\n# }\n\ninfsh app run infsh/higgs-audio --input input.json" }, { "title": "Use Cases", "body": "Voiceovers: Product demos, explainer videos\nAudiobooks: Convert text to spoken word\nPodcasts: Generate podcast episodes\nAccessibility: Make content accessible\nIVR: Phone system voice prompts\nVideo Narration: Add narration to videos" }, { "title": "Combine with Video", "body": "Generate speech, then create a talking head video:\n\n# 1. Generate speech\ninfsh app run infsh/kokoro-tts --input '{\"text\": \"Your script here\"}' > speech.json\n\n# 2. Use the audio URL with OmniHuman for avatar video\ninfsh app run bytedance/omnihuman-1-5 --input '{\n \"image_url\": \"https://portrait.jpg\",\n \"audio_url\": \"\"\n}'" }, { "title": "Related Skills", "body": "# Full platform skill (all 150+ apps)\nnpx skills add inference-sh/skills@inference-sh\n\n# AI avatars (combine TTS with talking heads)\nnpx skills add inference-sh/skills@ai-avatar-video\n\n# AI music generation\nnpx skills add inference-sh/skills@ai-music-generation\n\n# Speech-to-text (transcription)\nnpx skills add inference-sh/skills@speech-to-text\n\n# Video generation\nnpx skills add inference-sh/skills@ai-video-generation\n\nBrowse all apps: infsh app list" }, { "title": "Documentation", "body": "Running Apps - How to run apps via CLI\nAudio Transcription Example - Audio processing workflows\nApps Overview - Understanding the app ecosystem" } ], "body": "Text-to-Speech\n\nConvert text to natural speech via inference.sh CLI.\n\nQuick Start\n# Install CLI\ncurl -fsSL https://cli.inference.sh | sh && infsh login\n\n# Generate speech\ninfsh app run infsh/kokoro-tts --input '{\"text\": \"Hello, welcome to our product demo.\"}'\n\n\nInstall note: The install script only detects your OS/architecture, downloads the matching binary from dist.inference.sh, and verifies its SHA-256 checksum. No elevated permissions or background processes. Manual install & verification available.\n\nAvailable Models\nModel\tApp ID\tBest For\nDIA TTS\tinfsh/dia-tts\tConversational, expressive\nKokoro TTS\tinfsh/kokoro-tts\tFast, natural\nChatterbox\tinfsh/chatterbox\tGeneral purpose\nHiggs Audio\tinfsh/higgs-audio\tEmotional control\nVibeVoice\tinfsh/vibevoice\tPodcasts, long-form\nBrowse All Audio Apps\ninfsh app list --category audio\n\nExamples\nBasic Text-to-Speech\ninfsh app run infsh/kokoro-tts --input '{\"text\": \"Welcome to our tutorial.\"}'\n\nConversational TTS with DIA\ninfsh app sample infsh/dia-tts --save input.json\n\n# Edit input.json:\n# {\n# \"text\": \"Hey! How are you doing today? I'm really excited to share this with you.\",\n# \"voice\": \"conversational\"\n# }\n\ninfsh app run infsh/dia-tts --input input.json\n\nLong-form Audio (Podcasts)\ninfsh app sample infsh/vibevoice --save input.json\n\n# Edit input.json with your podcast script\ninfsh app run infsh/vibevoice --input input.json\n\nExpressive Speech with Higgs\ninfsh app sample infsh/higgs-audio --save input.json\n\n# {\n# \"text\": \"This is absolutely incredible!\",\n# \"emotion\": \"excited\"\n# }\n\ninfsh app run infsh/higgs-audio --input input.json\n\nUse Cases\nVoiceovers: Product demos, explainer videos\nAudiobooks: Convert text to spoken word\nPodcasts: Generate podcast episodes\nAccessibility: Make content accessible\nIVR: Phone system voice prompts\nVideo Narration: Add narration to videos\nCombine with Video\n\nGenerate speech, then create a talking head video:\n\n# 1. Generate speech\ninfsh app run infsh/kokoro-tts --input '{\"text\": \"Your script here\"}' > speech.json\n\n# 2. Use the audio URL with OmniHuman for avatar video\ninfsh app run bytedance/omnihuman-1-5 --input '{\n \"image_url\": \"https://portrait.jpg\",\n \"audio_url\": \"\"\n}'\n\nRelated Skills\n# Full platform skill (all 150+ apps)\nnpx skills add inference-sh/skills@inference-sh\n\n# AI avatars (combine TTS with talking heads)\nnpx skills add inference-sh/skills@ai-avatar-video\n\n# AI music generation\nnpx skills add inference-sh/skills@ai-music-generation\n\n# Speech-to-text (transcription)\nnpx skills add inference-sh/skills@speech-to-text\n\n# Video generation\nnpx skills add inference-sh/skills@ai-video-generation\n\n\nBrowse all apps: infsh app list\n\nDocumentation\nRunning Apps - How to run apps via CLI\nAudio Transcription Example - Audio processing workflows\nApps Overview - Understanding the app ecosystem" }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/okaris/text-to-speech", "publisherUrl": "https://clawhub.ai/okaris/text-to-speech", "owner": "okaris", "version": "0.1.5", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/text-to-speech", "downloadUrl": "https://openagent3.xyz/downloads/text-to-speech", "agentUrl": "https://openagent3.xyz/skills/text-to-speech/agent", "manifestUrl": "https://openagent3.xyz/skills/text-to-speech/agent.json", "briefUrl": "https://openagent3.xyz/skills/text-to-speech/agent.md" } }