{
  "schemaVersion": "1.0",
  "item": {
    "slug": "speakturbo-tts",
    "name": "Speak Turbo - Talk to your Claude 90ms latency!",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/EmZod/speakturbo-tts",
    "canonicalUrl": "https://clawhub.ai/EmZod/speakturbo-tts",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/speakturbo-tts",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=speakturbo-tts",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "speakturbo/daemon_streaming.py",
      "speakturbo/tests/__init__.py",
      "speakturbo/tests/test_daemon.py",
      "speakturbo/tests/test_cli.py",
      "speakturbo/__init__.py",
      "speakturbo/cli.py"
    ],
    "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/speakturbo-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/speakturbo-tts",
    "agentPageUrl": "https://openagent3.xyz/skills/speakturbo-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/speakturbo-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/speakturbo-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": "speakturbo - Talk to your Claude!",
        "body": "Give your agent the ability to speak to you real-time. Ultra-fast text-to-speech with ~90ms latency and 8 built-in voices."
      },
      {
        "title": "Quick Start",
        "body": "# Play immediately - you should hear \"Hello world\" through your speakers\nspeakturbo \"Hello world\"\n# Output: ⚡ 92ms → ▶ 93ms → ✓ 1245ms\n\n# Verify it's working by saving to file\nspeakturbo \"Hello world\" -o test.wav\nls -lh test.wav  # Should show ~50-100KB file\n\nOutput explained: ⚡ = first audio received, ▶ = playback started, ✓ = done"
      },
      {
        "title": "First Run",
        "body": "The first execution takes 2-5 seconds while the daemon starts and loads the model into memory. Subsequent calls are ~90ms to first sound.\n\n# First run (slow - daemon starting)\nspeakturbo \"Starting up\"  # ~2-5 seconds\n\n# Second run (fast - daemon already running)\nspeakturbo \"Now I'm fast\"  # ~90ms"
      },
      {
        "title": "Usage",
        "body": "# Basic - plays immediately (default voice: alba)\nspeakturbo \"Hello world\"\n\n# Save to file (no audio playback)\nspeakturbo \"Hello\" -o output.wav\n\n# Save to specific file\nspeakturbo \"Goodbye\" -o goodbye.wav\n\n# Quiet mode (suppress status messages, still plays audio)\nspeakturbo \"Hello\" -q\n\n# List available voices\nspeakturbo --list-voices"
      },
      {
        "title": "Available Voices",
        "body": "VoiceTypealbaFemale (default)mariusMalejavertMalejeanMalefantineFemalecosetteFemaleeponineFemaleazelmaFemale"
      },
      {
        "title": "Performance",
        "body": "MetricValueTime to first sound~90ms (daemon warm)First run2-5s (daemon startup)Real-time factor~4x fasterSample rate24kHz mono"
      },
      {
        "title": "Architecture",
        "body": "speakturbo (Rust CLI, 2.2MB)\n    │\n    │ HTTP streaming (port 7125)\n    ▼\nspeakturbo-daemon (Python + pocket-tts)\n    │\n    │ Model in memory, auto-shutdown after 1hr idle\n    ▼\nAudio playback (rodio)"
      },
      {
        "title": "Text Input",
        "body": "Encoding: UTF-8\nQuotes in text: Use escaping: speakturbo \"She said \\\"hello\\\"\"\nLong text: Supported, streams as it generates"
      },
      {
        "title": "Output Path Security",
        "body": "The -o flag only writes to directories that are on the allowlist. By default, these are:\n\n/tmp and system temp directories\nYour current working directory\n~/.speakturbo/\n\nIf you need to write elsewhere, use --allow-dir:\n\nspeakturbo \"Hello\" -o /custom/path/audio.wav --allow-dir /custom/path\n\nTo permanently allow a directory, add it to ~/.speakturbo/config:\n\nmkdir -p ~/.speakturbo && echo \"/custom/path\" >> ~/.speakturbo/config\n\nThe config file is one directory per line. Lines starting with # are comments."
      },
      {
        "title": "Exit Codes",
        "body": "CodeMeaning0Success (audio played/saved)1Error (daemon connection failed, invalid args)"
      },
      {
        "title": "When to Use",
        "body": "Use speakturbo when:\n\nYou need instant audio feedback (~90ms)\nSpeed matters more than voice variety\nBuilt-in voices are sufficient\n\nUse speak instead when:\n\nYou need custom voice cloning (Morgan Freeman, etc.)\n→ speak \"text\" --voice ~/.chatter/voices/morgan_freeman.wav\nYou need emotion tags like [laugh], [sigh]\nQuality/variety matters more than speed\n\nSee the speak skill documentation for full usage."
      },
      {
        "title": "Troubleshooting",
        "body": "No audio plays:\n\n# Check daemon is running\ncurl http://127.0.0.1:7125/health\n# Expected: {\"status\":\"ready\",\"voices\":[\"alba\",\"marius\",...]}\n\n# Verify by saving to file and playing manually\nspeakturbo \"test\" -o /tmp/test.wav\nafplay /tmp/test.wav  # macOS\naplay /tmp/test.wav   # Linux\n\nDaemon won't start:\n\n# Check port availability\nlsof -i :7125\n\n# Manually kill and restart\npkill -f \"daemon_streaming\"\nspeakturbo \"test\"  # Auto-restarts daemon\n\nFirst run is slow:\nThis is expected. The daemon needs to load the ~100MB model into memory. Subsequent calls will be fast (~90ms)."
      },
      {
        "title": "Daemon Management",
        "body": "The daemon auto-starts on first use and auto-shuts down after 1 hour idle.\n\n# Check status\ncurl http://127.0.0.1:7125/health\n\n# Manual stop\npkill -f \"daemon_streaming\"\n\n# View logs\ncat /tmp/speakturbo.log"
      },
      {
        "title": "Comparison with speak",
        "body": "FeaturespeakturbospeakTime to first sound~90ms~4-8sVoice cloning❌✅Emotion tags❌✅Voices8 built-inCustom wav filesEnginepocket-ttsChatterbox"
      }
    ],
    "body": "speakturbo - Talk to your Claude!\n\nGive your agent the ability to speak to you real-time. Ultra-fast text-to-speech with ~90ms latency and 8 built-in voices.\n\nQuick Start\n# Play immediately - you should hear \"Hello world\" through your speakers\nspeakturbo \"Hello world\"\n# Output: ⚡ 92ms → ▶ 93ms → ✓ 1245ms\n\n# Verify it's working by saving to file\nspeakturbo \"Hello world\" -o test.wav\nls -lh test.wav  # Should show ~50-100KB file\n\n\nOutput explained: ⚡ = first audio received, ▶ = playback started, ✓ = done\n\nFirst Run\n\nThe first execution takes 2-5 seconds while the daemon starts and loads the model into memory. Subsequent calls are ~90ms to first sound.\n\n# First run (slow - daemon starting)\nspeakturbo \"Starting up\"  # ~2-5 seconds\n\n# Second run (fast - daemon already running)\nspeakturbo \"Now I'm fast\"  # ~90ms\n\nUsage\n# Basic - plays immediately (default voice: alba)\nspeakturbo \"Hello world\"\n\n# Save to file (no audio playback)\nspeakturbo \"Hello\" -o output.wav\n\n# Save to specific file\nspeakturbo \"Goodbye\" -o goodbye.wav\n\n# Quiet mode (suppress status messages, still plays audio)\nspeakturbo \"Hello\" -q\n\n# List available voices\nspeakturbo --list-voices\n\nAvailable Voices\nVoice\tType\nalba\tFemale (default)\nmarius\tMale\njavert\tMale\njean\tMale\nfantine\tFemale\ncosette\tFemale\neponine\tFemale\nazelma\tFemale\nPerformance\nMetric\tValue\nTime to first sound\t~90ms (daemon warm)\nFirst run\t2-5s (daemon startup)\nReal-time factor\t~4x faster\nSample rate\t24kHz mono\nArchitecture\nspeakturbo (Rust CLI, 2.2MB)\n    │\n    │ HTTP streaming (port 7125)\n    ▼\nspeakturbo-daemon (Python + pocket-tts)\n    │\n    │ Model in memory, auto-shutdown after 1hr idle\n    ▼\nAudio playback (rodio)\n\nText Input\nEncoding: UTF-8\nQuotes in text: Use escaping: speakturbo \"She said \\\"hello\\\"\"\nLong text: Supported, streams as it generates\nOutput Path Security\n\nThe -o flag only writes to directories that are on the allowlist. By default, these are:\n\n/tmp and system temp directories\nYour current working directory\n~/.speakturbo/\n\nIf you need to write elsewhere, use --allow-dir:\n\nspeakturbo \"Hello\" -o /custom/path/audio.wav --allow-dir /custom/path\n\n\nTo permanently allow a directory, add it to ~/.speakturbo/config:\n\nmkdir -p ~/.speakturbo && echo \"/custom/path\" >> ~/.speakturbo/config\n\n\nThe config file is one directory per line. Lines starting with # are comments.\n\nExit Codes\nCode\tMeaning\n0\tSuccess (audio played/saved)\n1\tError (daemon connection failed, invalid args)\nWhen to Use\n\nUse speakturbo when:\n\nYou need instant audio feedback (~90ms)\nSpeed matters more than voice variety\nBuilt-in voices are sufficient\n\nUse speak instead when:\n\nYou need custom voice cloning (Morgan Freeman, etc.) → speak \"text\" --voice ~/.chatter/voices/morgan_freeman.wav\nYou need emotion tags like [laugh], [sigh]\nQuality/variety matters more than speed\n\nSee the speak skill documentation for full usage.\n\nTroubleshooting\n\nNo audio plays:\n\n# Check daemon is running\ncurl http://127.0.0.1:7125/health\n# Expected: {\"status\":\"ready\",\"voices\":[\"alba\",\"marius\",...]}\n\n# Verify by saving to file and playing manually\nspeakturbo \"test\" -o /tmp/test.wav\nafplay /tmp/test.wav  # macOS\naplay /tmp/test.wav   # Linux\n\n\nDaemon won't start:\n\n# Check port availability\nlsof -i :7125\n\n# Manually kill and restart\npkill -f \"daemon_streaming\"\nspeakturbo \"test\"  # Auto-restarts daemon\n\n\nFirst run is slow: This is expected. The daemon needs to load the ~100MB model into memory. Subsequent calls will be fast (~90ms).\n\nDaemon Management\n\nThe daemon auto-starts on first use and auto-shuts down after 1 hour idle.\n\n# Check status\ncurl http://127.0.0.1:7125/health\n\n# Manual stop\npkill -f \"daemon_streaming\"\n\n# View logs\ncat /tmp/speakturbo.log\n\nComparison with speak\nFeature\tspeakturbo\tspeak\nTime to first sound\t~90ms\t~4-8s\nVoice cloning\t❌\t✅\nEmotion tags\t❌\t✅\nVoices\t8 built-in\tCustom wav files\nEngine\tpocket-tts\tChatterbox"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/EmZod/speakturbo-tts",
    "publisherUrl": "https://clawhub.ai/EmZod/speakturbo-tts",
    "owner": "EmZod",
    "version": "1.0.7",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/speakturbo-tts",
    "downloadUrl": "https://openagent3.xyz/downloads/speakturbo-tts",
    "agentUrl": "https://openagent3.xyz/skills/speakturbo-tts/agent",
    "manifestUrl": "https://openagent3.xyz/skills/speakturbo-tts/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/speakturbo-tts/agent.md"
  }
}