{
  "schemaVersion": "1.0",
  "item": {
    "slug": "discord-voice-deepgram",
    "name": "Discord Voice Using Deepgram",
    "source": "tencent",
    "type": "skill",
    "category": "通讯协作",
    "sourceUrl": "https://clawhub.ai/adriel1006/discord-voice-deepgram",
    "canonicalUrl": "https://clawhub.ai/adriel1006/discord-voice-deepgram",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/discord-voice-deepgram",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=discord-voice-deepgram",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "clawdbot.plugin.json",
      "index.ts",
      "package.json",
      "SKILL.md",
      "tsconfig.json",
      "_meta.json"
    ],
    "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": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/discord-voice-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/discord-voice-deepgram",
    "agentPageUrl": "https://openagent3.xyz/skills/discord-voice-deepgram/agent",
    "manifestUrl": "https://openagent3.xyz/skills/discord-voice-deepgram/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/discord-voice-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": "Deepgram Discord Voice (Clawdbot/OpenClaw Plugin)",
        "body": "This plugin lets you talk to your agent only from a Discord voice channel.\n\nPipeline (low latency):\n\nDiscord voice audio → Deepgram streaming STT (WebSocket)\nTranscript → your agent\nAgent reply → Deepgram TTS (/v1/speak streamed HTTP Ogg/Opus)\nAudio played back into the voice channel"
      },
      {
        "title": "Requirements",
        "body": "A Discord bot token (DISCORD_TOKEN)\nA Deepgram API key (DEEPGRAM_API_KEY)\nDiscord bot permissions in your server:\n\nConnect\nSpeak\nUse Voice Activity"
      },
      {
        "title": "Option A: Install from ClawHub",
        "body": "In your OpenClaw/Clawdbot dashboard, open Skills/Plugins.\nAdd/install deepgram-discord-voice.\nSet the required environment variables."
      },
      {
        "title": "Option B: Manual install",
        "body": "Copy this folder into your extensions/plugins directory.\nRun:\n\nnpm install\n\nRestart OpenClaw/Clawdbot."
      },
      {
        "title": "Key settings",
        "body": "primaryUser (recommended): Who the bot listens to by default.\n\nBest: your Discord user ID (numeric)\nAlso supported: username/display name (e.g., atechy) if unique in-channel\n\n\n\nallowVoiceSwitch: If true, the primary user can switch who is allowed by voice.\n\n\nwakeWord: Prefix for voice control commands. Default: openclaw.\n\n\ndeepgram.sttModel: Default nova-2.\n\n\ndeepgram.language: Optional BCP‑47 language tag (e.g., en-US, es, es-EC).\n\n\nttsVoice: Deepgram Aura voice model (e.g., aura-2-thalia-en)."
      },
      {
        "title": "Example config",
        "body": "{\n  \"plugins\": {\n    \"entries\": {\n      \"deepgram-discord-voice\": {\n        \"enabled\": true,\n        \"config\": {\n          \"streamingSTT\": true,\n          \"streamingTTS\": true,\n\n          \"primaryUser\": \"atechy\",\n          \"allowVoiceSwitch\": true,\n          \"wakeWord\": \"openclaw\",\n\n          \"ttsVoice\": \"aura-2-thalia-en\",\n          \"vadSensitivity\": \"medium\",\n          \"bargeIn\": true,\n\n          \"deepgram\": {\n            \"sttModel\": \"nova-2\",\n            \"language\": \"en-US\"\n          }\n        }\n      }\n    }\n  }\n}"
      },
      {
        "title": "Join a voice channel",
        "body": "Use the plugin tool or slash command (depends on your OpenClaw setup):\n\nJoin: action=join with the channelId\nLeave: action=leave"
      },
      {
        "title": "Talk (voice channel)",
        "body": "Once the bot is connected, just speak."
      },
      {
        "title": "Safeguard: only listen to you (default)",
        "body": "When primaryUser is set, the plugin will only listen to that user unless you allow someone else."
      },
      {
        "title": "Let someone else talk (voice commands)",
        "body": "As the primary user, say:\n\nopenclaw allow <name>\nopenclaw listen to <name>\n\nTo lock it back:\n\nopenclaw only me\nopenclaw reset"
      },
      {
        "title": "Switch via tool actions (optional)",
        "body": "allow_speaker with user (id / @mention / name)\nonly_me\nstatus"
      },
      {
        "title": "Notes",
        "body": "Lowest latency comes from streamingSTT=true and streamingTTS=true.\nDeepgram TTS is streamed over HTTP in Ogg/Opus so Discord can play it immediately."
      }
    ],
    "body": "Deepgram Discord Voice (Clawdbot/OpenClaw Plugin)\n\nThis plugin lets you talk to your agent only from a Discord voice channel.\n\nPipeline (low latency):\n\nDiscord voice audio → Deepgram streaming STT (WebSocket)\nTranscript → your agent\nAgent reply → Deepgram TTS (/v1/speak streamed HTTP Ogg/Opus)\nAudio played back into the voice channel\nRequirements\nA Discord bot token (DISCORD_TOKEN)\nA Deepgram API key (DEEPGRAM_API_KEY)\nDiscord bot permissions in your server:\nConnect\nSpeak\nUse Voice Activity\nInstall\nOption A: Install from ClawHub\nIn your OpenClaw/Clawdbot dashboard, open Skills/Plugins.\nAdd/install deepgram-discord-voice.\nSet the required environment variables.\nOption B: Manual install\nCopy this folder into your extensions/plugins directory.\nRun:\nnpm install\n\nRestart OpenClaw/Clawdbot.\nConfiguration\nKey settings\n\nprimaryUser (recommended): Who the bot listens to by default.\n\nBest: your Discord user ID (numeric)\nAlso supported: username/display name (e.g., atechy) if unique in-channel\n\nallowVoiceSwitch: If true, the primary user can switch who is allowed by voice.\n\nwakeWord: Prefix for voice control commands. Default: openclaw.\n\ndeepgram.sttModel: Default nova-2.\n\ndeepgram.language: Optional BCP‑47 language tag (e.g., en-US, es, es-EC).\n\nttsVoice: Deepgram Aura voice model (e.g., aura-2-thalia-en).\n\nExample config\n{\n  \"plugins\": {\n    \"entries\": {\n      \"deepgram-discord-voice\": {\n        \"enabled\": true,\n        \"config\": {\n          \"streamingSTT\": true,\n          \"streamingTTS\": true,\n\n          \"primaryUser\": \"atechy\",\n          \"allowVoiceSwitch\": true,\n          \"wakeWord\": \"openclaw\",\n\n          \"ttsVoice\": \"aura-2-thalia-en\",\n          \"vadSensitivity\": \"medium\",\n          \"bargeIn\": true,\n\n          \"deepgram\": {\n            \"sttModel\": \"nova-2\",\n            \"language\": \"en-US\"\n          }\n        }\n      }\n    }\n  }\n}\n\nUsage\nJoin a voice channel\n\nUse the plugin tool or slash command (depends on your OpenClaw setup):\n\nJoin: action=join with the channelId\nLeave: action=leave\nTalk (voice channel)\n\nOnce the bot is connected, just speak.\n\nSafeguard: only listen to you (default)\n\nWhen primaryUser is set, the plugin will only listen to that user unless you allow someone else.\n\nLet someone else talk (voice commands)\n\nAs the primary user, say:\n\nopenclaw allow <name>\nopenclaw listen to <name>\n\nTo lock it back:\n\nopenclaw only me\nopenclaw reset\nSwitch via tool actions (optional)\nallow_speaker with user (id / @mention / name)\nonly_me\nstatus\nNotes\nLowest latency comes from streamingSTT=true and streamingTTS=true.\nDeepgram TTS is streamed over HTTP in Ogg/Opus so Discord can play it immediately."
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/adriel1006/discord-voice-deepgram",
    "publisherUrl": "https://clawhub.ai/adriel1006/discord-voice-deepgram",
    "owner": "adriel1006",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/discord-voice-deepgram",
    "downloadUrl": "https://openagent3.xyz/downloads/discord-voice-deepgram",
    "agentUrl": "https://openagent3.xyz/skills/discord-voice-deepgram/agent",
    "manifestUrl": "https://openagent3.xyz/skills/discord-voice-deepgram/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/discord-voice-deepgram/agent.md"
  }
}