{
  "schemaVersion": "1.0",
  "item": {
    "slug": "parakeet-stt",
    "name": "Parakeet Stt",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/carlulsoe/parakeet-stt",
    "canonicalUrl": "https://clawhub.ai/carlulsoe/parakeet-stt",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/parakeet-stt",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=parakeet-stt",
    "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": "2026-04-30T16:55:25.780Z",
      "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/parakeet-stt"
    },
    "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/parakeet-stt",
    "agentPageUrl": "https://openagent3.xyz/skills/parakeet-stt/agent",
    "manifestUrl": "https://openagent3.xyz/skills/parakeet-stt/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/parakeet-stt/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": "Parakeet TDT (Speech-to-Text)",
        "body": "Local transcription using NVIDIA Parakeet TDT 0.6B v3 with ONNX Runtime.\nRuns on CPU — no GPU required. ~30x faster than realtime."
      },
      {
        "title": "Installation",
        "body": "# Clone the repo\ngit clone https://github.com/groxaxo/parakeet-tdt-0.6b-v3-fastapi-openai.git\ncd parakeet-tdt-0.6b-v3-fastapi-openai\n\n# Run with Docker (recommended)\ndocker compose up -d parakeet-cpu\n\n# Or run directly with Python\npip install -r requirements.txt\nuvicorn app.main:app --host 0.0.0.0 --port 5000\n\nDefault port is 5000. Set PARAKEET_URL to override (e.g., http://localhost:5092)."
      },
      {
        "title": "API Endpoint",
        "body": "OpenAI-compatible API at $PARAKEET_URL (default: http://localhost:5000)."
      },
      {
        "title": "Quick Start",
        "body": "# Transcribe audio file (plain text)\ncurl -X POST $PARAKEET_URL/v1/audio/transcriptions \\\n  -F \"file=@/path/to/audio.mp3\" \\\n  -F \"response_format=text\"\n\n# Get timestamps and segments\ncurl -X POST $PARAKEET_URL/v1/audio/transcriptions \\\n  -F \"file=@/path/to/audio.mp3\" \\\n  -F \"response_format=verbose_json\"\n\n# Generate subtitles (SRT)\ncurl -X POST $PARAKEET_URL/v1/audio/transcriptions \\\n  -F \"file=@/path/to/audio.mp3\" \\\n  -F \"response_format=srt\""
      },
      {
        "title": "Python / OpenAI SDK",
        "body": "import os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    base_url=os.getenv(\"PARAKEET_URL\", \"http://localhost:5000\") + \"/v1\",\n    api_key=\"not-needed\"\n)\n\nwith open(\"audio.mp3\", \"rb\") as f:\n    transcript = client.audio.transcriptions.create(\n        model=\"parakeet-tdt-0.6b-v3\",\n        file=f,\n        response_format=\"text\"\n    )\nprint(transcript)"
      },
      {
        "title": "Response Formats",
        "body": "FormatOutputtextPlain textjson{\"text\": \"...\"}verbose_jsonSegments with timestamps and wordssrtSRT subtitlesvttWebVTT subtitles"
      },
      {
        "title": "Supported Languages (25)",
        "body": "English, Spanish, French, German, Italian, Portuguese, Polish, Russian,\nUkrainian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Czech,\nRomanian, Hungarian, Bulgarian, Slovak, Croatian, Lithuanian, Latvian,\nEstonian, Slovenian\n\nLanguage is auto-detected — no configuration needed."
      },
      {
        "title": "Web Interface",
        "body": "Open $PARAKEET_URL in a browser for drag-and-drop transcription UI."
      },
      {
        "title": "Docker Management",
        "body": "# Check status\ndocker ps --filter \"name=parakeet\"\n\n# View logs\ndocker logs -f <container-name>\n\n# Restart\ndocker compose restart\n\n# Stop\ndocker compose down"
      },
      {
        "title": "Why Parakeet over Whisper?",
        "body": "Speed: ~30x faster than realtime on CPU\nAccuracy: Comparable to Whisper large-v3\nPrivacy: Runs 100% locally, no cloud calls\nCompatibility: Drop-in replacement for OpenAI's transcription API"
      }
    ],
    "body": "Parakeet TDT (Speech-to-Text)\n\nLocal transcription using NVIDIA Parakeet TDT 0.6B v3 with ONNX Runtime. Runs on CPU — no GPU required. ~30x faster than realtime.\n\nInstallation\n# Clone the repo\ngit clone https://github.com/groxaxo/parakeet-tdt-0.6b-v3-fastapi-openai.git\ncd parakeet-tdt-0.6b-v3-fastapi-openai\n\n# Run with Docker (recommended)\ndocker compose up -d parakeet-cpu\n\n# Or run directly with Python\npip install -r requirements.txt\nuvicorn app.main:app --host 0.0.0.0 --port 5000\n\n\nDefault port is 5000. Set PARAKEET_URL to override (e.g., http://localhost:5092).\n\nAPI Endpoint\n\nOpenAI-compatible API at $PARAKEET_URL (default: http://localhost:5000).\n\nQuick Start\n# Transcribe audio file (plain text)\ncurl -X POST $PARAKEET_URL/v1/audio/transcriptions \\\n  -F \"file=@/path/to/audio.mp3\" \\\n  -F \"response_format=text\"\n\n# Get timestamps and segments\ncurl -X POST $PARAKEET_URL/v1/audio/transcriptions \\\n  -F \"file=@/path/to/audio.mp3\" \\\n  -F \"response_format=verbose_json\"\n\n# Generate subtitles (SRT)\ncurl -X POST $PARAKEET_URL/v1/audio/transcriptions \\\n  -F \"file=@/path/to/audio.mp3\" \\\n  -F \"response_format=srt\"\n\nPython / OpenAI SDK\nimport os\nfrom openai import OpenAI\n\nclient = OpenAI(\n    base_url=os.getenv(\"PARAKEET_URL\", \"http://localhost:5000\") + \"/v1\",\n    api_key=\"not-needed\"\n)\n\nwith open(\"audio.mp3\", \"rb\") as f:\n    transcript = client.audio.transcriptions.create(\n        model=\"parakeet-tdt-0.6b-v3\",\n        file=f,\n        response_format=\"text\"\n    )\nprint(transcript)\n\nResponse Formats\nFormat\tOutput\ntext\tPlain text\njson\t{\"text\": \"...\"}\nverbose_json\tSegments with timestamps and words\nsrt\tSRT subtitles\nvtt\tWebVTT subtitles\nSupported Languages (25)\n\nEnglish, Spanish, French, German, Italian, Portuguese, Polish, Russian, Ukrainian, Dutch, Swedish, Danish, Finnish, Norwegian, Greek, Czech, Romanian, Hungarian, Bulgarian, Slovak, Croatian, Lithuanian, Latvian, Estonian, Slovenian\n\nLanguage is auto-detected — no configuration needed.\n\nWeb Interface\n\nOpen $PARAKEET_URL in a browser for drag-and-drop transcription UI.\n\nDocker Management\n# Check status\ndocker ps --filter \"name=parakeet\"\n\n# View logs\ndocker logs -f <container-name>\n\n# Restart\ndocker compose restart\n\n# Stop\ndocker compose down\n\nWhy Parakeet over Whisper?\nSpeed: ~30x faster than realtime on CPU\nAccuracy: Comparable to Whisper large-v3\nPrivacy: Runs 100% locally, no cloud calls\nCompatibility: Drop-in replacement for OpenAI's transcription API"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/carlulsoe/parakeet-stt",
    "publisherUrl": "https://clawhub.ai/carlulsoe/parakeet-stt",
    "owner": "carlulsoe",
    "version": "1.1.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/parakeet-stt",
    "downloadUrl": "https://openagent3.xyz/downloads/parakeet-stt",
    "agentUrl": "https://openagent3.xyz/skills/parakeet-stt/agent",
    "manifestUrl": "https://openagent3.xyz/skills/parakeet-stt/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/parakeet-stt/agent.md"
  }
}