{
  "schemaVersion": "1.0",
  "item": {
    "slug": "deepgram",
    "name": "DeepGram Speech platform",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/nerkn/deepgram",
    "canonicalUrl": "https://clawhub.ai/nerkn/deepgram",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/deepgram",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=deepgram",
    "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",
      "slug": "deepgram",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-02T10:39:16.905Z",
      "expiresAt": "2026-05-09T10:39:16.905Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=deepgram",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=deepgram",
        "contentDisposition": "attachment; filename=\"deepgram-1.0.1.zip\"",
        "redirectLocation": null,
        "bodySnippet": null,
        "slug": "deepgram"
      },
      "scope": "item",
      "summary": "Item download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this item.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/deepgram"
    },
    "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/deepgram",
    "agentPageUrl": "https://openagent3.xyz/skills/deepgram/agent",
    "manifestUrl": "https://openagent3.xyz/skills/deepgram/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/deepgram/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": "Tool",
        "body": "@deepgram/cli — command-line interface for Deepgram speech-to-text."
      },
      {
        "title": "Install",
        "body": "npm install -g @deepgram/cli"
      },
      {
        "title": "Auth",
        "body": "deepgram login\n\nUses your Deepgram API key (stored locally)."
      },
      {
        "title": "Transcribe a Local Audio File",
        "body": "deepgram listen prerecorded audio.wav"
      },
      {
        "title": "Transcribe with Options",
        "body": "deepgram listen prerecorded audio.wav \\\n  --model nova-2 \\\n  --language en \\\n  --punctuate \\\n  --diarize"
      },
      {
        "title": "From URL (remote audio)",
        "body": "deepgram listen prerecorded https://example.com/audio.mp3"
      },
      {
        "title": "From STDIN (pipes)",
        "body": "cat audio.wav | deepgram listen prerecorded -"
      },
      {
        "title": "From Microphone (live)",
        "body": "deepgram listen microphone\n\nStop with Ctrl+C. Congrats, you just dictated reality."
      },
      {
        "title": "Save Transcript",
        "body": "deepgram listen prerecorded audio.wav > transcript.json"
      },
      {
        "title": "Plain Text Output",
        "body": "deepgram listen prerecorded audio.wav --format text"
      },
      {
        "title": "Useful Flags (Memorize These)",
        "body": "--model – nova-2, general, etc.\n--language – en, tr, de, …\n--punctuate – adds punctuation\n--diarize – speaker separation\n--format – json, text, srt, vtt"
      },
      {
        "title": "Typical Workflow",
        "body": "Reach content (file / URL / mic)\nRun deepgram listen\nCapture output (JSON or text)\nPost-process (search, summarize, subtitle)"
      },
      {
        "title": "Skill Summary",
        "body": "CLI-based speech-to-text\nLocal, remote, and live audio\nScriptable, pipe-friendly\nFast, accurate, no UI nonsense\n\nDeepgram CLI: because keyboards are overrated."
      }
    ],
    "body": "Deepgram CLI Skills Guide\nTool\n\n@deepgram/cli — command-line interface for Deepgram speech-to-text.\n\nInstall\nnpm install -g @deepgram/cli\n\nAuth\ndeepgram login\n\n\nUses your Deepgram API key (stored locally).\n\nCore Skill: Speech → Text\nTranscribe a Local Audio File\ndeepgram listen prerecorded audio.wav\n\nTranscribe with Options\ndeepgram listen prerecorded audio.wav \\\n  --model nova-2 \\\n  --language en \\\n  --punctuate \\\n  --diarize\n\nCore Skill: Read / Reach Content\nFrom URL (remote audio)\ndeepgram listen prerecorded https://example.com/audio.mp3\n\nFrom STDIN (pipes)\ncat audio.wav | deepgram listen prerecorded -\n\nFrom Microphone (live)\ndeepgram listen microphone\n\n\nStop with Ctrl+C. Congrats, you just dictated reality.\n\nOutput Handling\nSave Transcript\ndeepgram listen prerecorded audio.wav > transcript.json\n\nPlain Text Output\ndeepgram listen prerecorded audio.wav --format text\n\nUseful Flags (Memorize These)\n--model – nova-2, general, etc.\n--language – en, tr, de, …\n--punctuate – adds punctuation\n--diarize – speaker separation\n--format – json, text, srt, vtt\nTypical Workflow\nReach content (file / URL / mic)\nRun deepgram listen\nCapture output (JSON or text)\nPost-process (search, summarize, subtitle)\nSkill Summary\nCLI-based speech-to-text\nLocal, remote, and live audio\nScriptable, pipe-friendly\nFast, accurate, no UI nonsense\n\nDeepgram CLI: because keyboards are overrated."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/nerkn/deepgram",
    "publisherUrl": "https://clawhub.ai/nerkn/deepgram",
    "owner": "nerkn",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/deepgram",
    "downloadUrl": "https://openagent3.xyz/downloads/deepgram",
    "agentUrl": "https://openagent3.xyz/skills/deepgram/agent",
    "manifestUrl": "https://openagent3.xyz/skills/deepgram/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/deepgram/agent.md"
  }
}