{
  "schemaVersion": "1.0",
  "item": {
    "slug": "pocket-tts",
    "name": "Pocket Tts",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/sherajdev/pocket-tts",
    "canonicalUrl": "https://clawhub.ai/sherajdev/pocket-tts",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/pocket-tts",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=pocket-tts",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "cli.py",
      "install.sh",
      "test.sh"
    ],
    "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": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-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/pocket-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/pocket-tts",
    "agentPageUrl": "https://openagent3.xyz/skills/pocket-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pocket-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pocket-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": "Pocket TTS Skill",
        "body": "Fully local, offline text-to-speech using Kyutai's Pocket TTS model. Generate high-quality audio from text without any API calls or internet connection. Features 8 built-in voices, voice cloning support, and runs entirely on CPU."
      },
      {
        "title": "Features",
        "body": "🎯 Fully local - No API calls, runs completely offline\n🚀 CPU-only - No GPU required, works on any computer\n⚡ Fast generation - ~2-6x real-time on CPU\n🎤 8 built-in voices - alba, marius, javert, jean, fantine, cosette, eponine, azelma\n🎭 Voice cloning - Clone any voice from a WAV sample\n🔊 Low latency - ~200ms first audio chunk\n📚 Simple Python API - Easy integration into any project"
      },
      {
        "title": "Installation",
        "body": "# 1. Accept the model license on Hugging Face\n# https://huggingface.co/kyutai/pocket-tts\n\n# 2. Install the package\npip install pocket-tts\n\n# Or use uv for automatic dependency management\nuvx pocket-tts generate \"Hello world\""
      },
      {
        "title": "CLI",
        "body": "# Basic usage\npocket-tts \"Hello, I am your AI assistant\"\n\n# With specific voice\npocket-tts \"Hello\" --voice alba --output hello.wav\n\n# With custom voice file (voice cloning)\npocket-tts \"Hello\" --voice-file myvoice.wav --output output.wav\n\n# Adjust speed\npocket-tts \"Hello\" --speed 1.2\n\n# Start local server\npocket-tts --serve\n\n# List available voices\npocket-tts --list-voices"
      },
      {
        "title": "Python API",
        "body": "from pocket_tts import TTSModel\nimport scipy.io.wavfile\n\n# Load model\ntts_model = TTSModel.load_model()\n\n# Get voice state\nvoice_state = tts_model.get_state_for_audio_prompt(\n    \"hf://kyutai/tts-voices/alba-mackenna/casual.wav\"\n)\n\n# Generate audio\naudio = tts_model.generate_audio(voice_state, \"Hello world!\")\n\n# Save to WAV\nscipy.io.wavfile.write(\"output.wav\", tts_model.sample_rate, audio.numpy())\n\n# Check sample rate\nprint(f\"Sample rate: {tts_model.sample_rate} Hz\")"
      },
      {
        "title": "Available Voices",
        "body": "VoiceDescriptionalbaCasual female voicemariusMale voicejavertClear male voicejeanNatural male voicefantineFemale voicecosetteFemale voiceeponineFemale voiceazelmaFemale voice\n\nOr use --voice-file /path/to/wav.wav for custom voice cloning."
      },
      {
        "title": "Options",
        "body": "OptionDescriptionDefaulttextText to convertRequired-o, --outputOutput WAV fileoutput.wav-v, --voiceVoice presetalba-s, --speedSpeech speed (0.5-2.0)1.0--voice-fileCustom WAV for cloningNone--serveStart HTTP serverFalse--list-voicesList all voicesFalse"
      },
      {
        "title": "Requirements",
        "body": "Python 3.10-3.14\nPyTorch 2.5+ (CPU version works)\nWorks on 2 CPU cores"
      },
      {
        "title": "Notes",
        "body": "⚠️ Model is gated - accept license on Hugging Face first\n🌍 English language only (v1)\n💾 First run downloads model (~100M parameters)\n🔊 Audio is returned as 1D torch tensor (PCM data)"
      },
      {
        "title": "Links",
        "body": "Demo\nGitHub\nHugging Face\nPaper"
      }
    ],
    "body": "Pocket TTS Skill\n\nFully local, offline text-to-speech using Kyutai's Pocket TTS model. Generate high-quality audio from text without any API calls or internet connection. Features 8 built-in voices, voice cloning support, and runs entirely on CPU.\n\nFeatures\n🎯 Fully local - No API calls, runs completely offline\n🚀 CPU-only - No GPU required, works on any computer\n⚡ Fast generation - ~2-6x real-time on CPU\n🎤 8 built-in voices - alba, marius, javert, jean, fantine, cosette, eponine, azelma\n🎭 Voice cloning - Clone any voice from a WAV sample\n🔊 Low latency - ~200ms first audio chunk\n📚 Simple Python API - Easy integration into any project\nInstallation\n# 1. Accept the model license on Hugging Face\n# https://huggingface.co/kyutai/pocket-tts\n\n# 2. Install the package\npip install pocket-tts\n\n# Or use uv for automatic dependency management\nuvx pocket-tts generate \"Hello world\"\n\nUsage\nCLI\n# Basic usage\npocket-tts \"Hello, I am your AI assistant\"\n\n# With specific voice\npocket-tts \"Hello\" --voice alba --output hello.wav\n\n# With custom voice file (voice cloning)\npocket-tts \"Hello\" --voice-file myvoice.wav --output output.wav\n\n# Adjust speed\npocket-tts \"Hello\" --speed 1.2\n\n# Start local server\npocket-tts --serve\n\n# List available voices\npocket-tts --list-voices\n\nPython API\nfrom pocket_tts import TTSModel\nimport scipy.io.wavfile\n\n# Load model\ntts_model = TTSModel.load_model()\n\n# Get voice state\nvoice_state = tts_model.get_state_for_audio_prompt(\n    \"hf://kyutai/tts-voices/alba-mackenna/casual.wav\"\n)\n\n# Generate audio\naudio = tts_model.generate_audio(voice_state, \"Hello world!\")\n\n# Save to WAV\nscipy.io.wavfile.write(\"output.wav\", tts_model.sample_rate, audio.numpy())\n\n# Check sample rate\nprint(f\"Sample rate: {tts_model.sample_rate} Hz\")\n\nAvailable Voices\nVoice\tDescription\nalba\tCasual female voice\nmarius\tMale voice\njavert\tClear male voice\njean\tNatural male voice\nfantine\tFemale voice\ncosette\tFemale voice\neponine\tFemale voice\nazelma\tFemale voice\n\nOr use --voice-file /path/to/wav.wav for custom voice cloning.\n\nOptions\nOption\tDescription\tDefault\ntext\tText to convert\tRequired\n-o, --output\tOutput WAV file\toutput.wav\n-v, --voice\tVoice preset\talba\n-s, --speed\tSpeech speed (0.5-2.0)\t1.0\n--voice-file\tCustom WAV for cloning\tNone\n--serve\tStart HTTP server\tFalse\n--list-voices\tList all voices\tFalse\nRequirements\nPython 3.10-3.14\nPyTorch 2.5+ (CPU version works)\nWorks on 2 CPU cores\nNotes\n⚠️ Model is gated - accept license on Hugging Face first\n🌍 English language only (v1)\n💾 First run downloads model (~100M parameters)\n🔊 Audio is returned as 1D torch tensor (PCM data)\nLinks\nDemo\nGitHub\nHugging Face\nPaper"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/sherajdev/pocket-tts",
    "publisherUrl": "https://clawhub.ai/sherajdev/pocket-tts",
    "owner": "sherajdev",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/pocket-tts",
    "downloadUrl": "https://openagent3.xyz/downloads/pocket-tts",
    "agentUrl": "https://openagent3.xyz/skills/pocket-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/pocket-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/pocket-tts/agent.md"
  }
}