{
  "schemaVersion": "1.0",
  "item": {
    "slug": "minimax-to-telegram",
    "name": "For using minimax mcp to generate audio, image, video to telegram.",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/hoyin258/minimax-to-telegram",
    "canonicalUrl": "https://clawhub.ai/hoyin258/minimax-to-telegram",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/minimax-to-telegram",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=minimax-to-telegram",
    "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/minimax-to-telegram"
    },
    "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/minimax-to-telegram",
    "agentPageUrl": "https://openagent3.xyz/skills/minimax-to-telegram/agent",
    "manifestUrl": "https://openagent3.xyz/skills/minimax-to-telegram/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/minimax-to-telegram/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": "1. Install mcporter",
        "body": "# 如果未有 npm/npx\nnpm install -g mcporter\n\n或者用 npx 直接跑：\n\nnpx mcporter --help"
      },
      {
        "title": "2. Set MiniMax API Key",
        "body": "响 terminal 度 set 環境變數：\n\nexport MINIMAX_API_KEY=\"your-api-key-here\"\n\n或者响 ~/.mcporter/config.json 入面 set：\n\n{\n  \"env\": {\n    \"MINIMAX_API_KEY\": \"your-api-key-here\",\n    \"MINIMAX_RESOURCE_MODE\": \"url\"\n  }\n}"
      },
      {
        "title": "3. Add MiniMax MCP Server",
        "body": "mcporter mcp add minimax-mcp"
      },
      {
        "title": "MiniMax MCP Skill",
        "body": "Use mcporter to call MiniMax MCP server tools."
      },
      {
        "title": "Prerequisites",
        "body": "mcporter CLI installed\nMiniMax MCP server configured in mcporter"
      },
      {
        "title": "Available Tools",
        "body": "ToolDescriptiontext_to_imageGenerate images from text promptstext_to_audioConvert text to speech (TTS)generate_videoGenerate videos from text promptsimage_to_videoGenerate videos from imagesmusic_generationGenerate music from prompt + lyricsvoice_cloneClone voice from audio filevoice_designGenerate voice from descriptionlist_voicesList available voice IDsplay_audioPlay audio file"
      },
      {
        "title": "Image Generation",
        "body": "mcporter call minimax-mcp.text_to_image prompt:\"your prompt\" aspectRatio:\"4:3\""
      },
      {
        "title": "Audio Generation (TTS)",
        "body": "mcporter call minimax-mcp.text_to_audio text:\"Hello world\" voiceId:\"male-qn-qingse\""
      },
      {
        "title": "Video Generation",
        "body": "mcporter call minimax-mcp.generate_video prompt:\"your video description\""
      },
      {
        "title": "Sending to Telegram",
        "body": "IMPORTANT: When MiniMax returns a URL, it includes a query string with authentication token. You MUST use the FULL URL including all query parameters.\n\nCorrect (full URL with token):\n\n<MINIMAX_OUTPUT_URL>?Expires=xxx&OSSAccessKeyId=xxx&Signature=xxx\n\nIncorrect (URL without token):\n\n<MINIMAX_OUTPUT_URL>"
      },
      {
        "title": "Sending Image to Telegram",
        "body": "Call text_to_image and capture the FULL URL (including query string)\nSend directly to Telegram using message tool with media parameter:\n\nmessage(\n  action=\"send\",\n  channel=\"telegram\",\n  target=\"<chat_id>\",\n  media=\"<full_url_with_token>\",\n  message=\"Your caption\"\n)"
      },
      {
        "title": "Sending Audio to Telegram",
        "body": "Same approach - use FULL URL with token:\n\nmessage(\n  action=\"send\",\n  channel=\"telegram\",\n  target=\"<chat_id>\",\n  media=\"<full_url_with_token>\",\n  message=\"Your caption\"\n)\n\nIMPORTANT: When sending audio, ALWAYS include the text content as the message caption below the audio!\n\nExample:\n\n# Generate audio\naudio_url = \"<MINIMAX_AUDIO_URL>?Expires=xxx&Signature=xxx\"\ntext_content = \"呢段係你想既文字內容...\"\n\n# Send with both audio and text\nmessage(\n  action=\"send\",\n  channel=\"telegram\",\n  target=\"<chat_id>\",\n  media=audio_url,\n  message=text_content  # Always include the text!\n)"
      },
      {
        "title": "text_to_image",
        "body": "prompt: Text description of desired image\naspectRatio: \"1:1\", \"16:9\", \"4:3\", \"3:2\", \"2:3\", \"3:4\", \"9:16\", \"21:9\"\nn: Number of images (1-9)\nmodel: Model to use (default: \"image-01\")"
      },
      {
        "title": "text_to_audio",
        "body": "text: Text to convert to speech\nvoiceId: Voice ID (e.g., \"male-qn-qingse\", \"female-shaonv\")\nspeed: Speech speed (0.5-2)\nemotion: \"happy\", \"sad\", \"angry\", \"fearful\", \"disgusted\", \"surprised\", \"neutral\"\nformat: \"mp3\", \"wav\", \"pcm\", \"flac\"\nlanguageBoost: Enhance recognition for specific languages/dialects\n\nCantonese: \"Chinese,Yue\" or \"Chinese\"\nMandarin: \"Chinese\" or \"Chinese,Mandarin\"\nEnglish: \"English\"\nAlways include this when generating Cantonese audio!"
      },
      {
        "title": "generate_video",
        "body": "prompt: Video description\nmodel: \"T2V-01\", \"T2V-01-Director\", \"I2V-01\", \"I2V-01-Director\", \"I2V-01-live\", \"MiniMax-Hailuo-02\"\nduration: 6 or 10 (for MiniMax-Hailuo-02)\nresolution: \"768P\", \"1080P\""
      },
      {
        "title": "Optimization & Troubleshooting",
        "body": "Timeout Management: Video generation can take significant time (up to 20-30 minutes for high-quality 10s clips). Always pass a large --timeout value (e.g., --timeout 1800000) to mcporter to prevent early termination.\nGateway Turn Limit: Most OpenClaw profiles have a 10-minute turn timeout (600000ms). To avoid being killed by the gateway, ALWAYS run generate_video with background: true or inside a background process.\nModel Choice: Use MiniMax-Hailuo-02 for higher quality 10-second videos."
      },
      {
        "title": "Error Handling",
        "body": "If you get 403 Forbidden when sending to Telegram:\n\nMake sure you're using the FULL URL with query string\nThe token (Signature) expires - regenerate if needed"
      },
      {
        "title": "Notes",
        "body": "MiniMax MCP must be configured with MINIMAX_RESOURCE_MODE=url in mcporter config\nGenerated media URLs include authentication tokens that expire\nAlways use the complete URL returned by MCP calls"
      },
      {
        "title": "Cantonese (廣東話) Tips",
        "body": "When generating Cantonese audio:\n\nUse voice ID from Cantonese category (e.g., \"Cantonese_PlayfulMan\", \"Cantonese_CuteGirl\")\nAlways add: languageBoost:\"Chinese,Yue\" or languageBoost:\"Chinese\"\nExample:\nmcporter call minimax-mcp.text_to_audio text:\"新年快樂\" voiceId:\"Cantonese_PlayfulMan\" languageBoost:\"Chinese,Yue\""
      }
    ],
    "body": "Setup (Prerequisites)\n1. Install mcporter\n# 如果未有 npm/npx\nnpm install -g mcporter\n\n\n或者用 npx 直接跑：\n\nnpx mcporter --help\n\n2. Set MiniMax API Key\n\n响 terminal 度 set 環境變數：\n\nexport MINIMAX_API_KEY=\"your-api-key-here\"\n\n\n或者响 ~/.mcporter/config.json 入面 set：\n\n{\n  \"env\": {\n    \"MINIMAX_API_KEY\": \"your-api-key-here\",\n    \"MINIMAX_RESOURCE_MODE\": \"url\"\n  }\n}\n\n3. Add MiniMax MCP Server\nmcporter mcp add minimax-mcp\n\nMiniMax MCP Skill\n\nUse mcporter to call MiniMax MCP server tools.\n\nPrerequisites\nmcporter CLI installed\nMiniMax MCP server configured in mcporter\nAvailable Tools\nTool\tDescription\ntext_to_image\tGenerate images from text prompts\ntext_to_audio\tConvert text to speech (TTS)\ngenerate_video\tGenerate videos from text prompts\nimage_to_video\tGenerate videos from images\nmusic_generation\tGenerate music from prompt + lyrics\nvoice_clone\tClone voice from audio file\nvoice_design\tGenerate voice from description\nlist_voices\tList available voice IDs\nplay_audio\tPlay audio file\nBasic Usage\nImage Generation\nmcporter call minimax-mcp.text_to_image prompt:\"your prompt\" aspectRatio:\"4:3\"\n\nAudio Generation (TTS)\nmcporter call minimax-mcp.text_to_audio text:\"Hello world\" voiceId:\"male-qn-qingse\"\n\nVideo Generation\nmcporter call minimax-mcp.generate_video prompt:\"your video description\"\n\nSending to Telegram\n\nIMPORTANT: When MiniMax returns a URL, it includes a query string with authentication token. You MUST use the FULL URL including all query parameters.\n\nCorrect (full URL with token):\n\n<MINIMAX_OUTPUT_URL>?Expires=xxx&OSSAccessKeyId=xxx&Signature=xxx\n\n\nIncorrect (URL without token):\n\n<MINIMAX_OUTPUT_URL>\n\nSending Image to Telegram\nCall text_to_image and capture the FULL URL (including query string)\nSend directly to Telegram using message tool with media parameter:\nmessage(\n  action=\"send\",\n  channel=\"telegram\",\n  target=\"<chat_id>\",\n  media=\"<full_url_with_token>\",\n  message=\"Your caption\"\n)\n\nSending Audio to Telegram\n\nSame approach - use FULL URL with token:\n\nmessage(\n  action=\"send\",\n  channel=\"telegram\",\n  target=\"<chat_id>\",\n  media=\"<full_url_with_token>\",\n  message=\"Your caption\"\n)\n\n\nIMPORTANT: When sending audio, ALWAYS include the text content as the message caption below the audio!\n\nExample:\n\n# Generate audio\naudio_url = \"<MINIMAX_AUDIO_URL>?Expires=xxx&Signature=xxx\"\ntext_content = \"呢段係你想既文字內容...\"\n\n# Send with both audio and text\nmessage(\n  action=\"send\",\n  channel=\"telegram\",\n  target=\"<chat_id>\",\n  media=audio_url,\n  message=text_content  # Always include the text!\n)\n\nCommon Parameters\ntext_to_image\nprompt: Text description of desired image\naspectRatio: \"1:1\", \"16:9\", \"4:3\", \"3:2\", \"2:3\", \"3:4\", \"9:16\", \"21:9\"\nn: Number of images (1-9)\nmodel: Model to use (default: \"image-01\")\ntext_to_audio\ntext: Text to convert to speech\nvoiceId: Voice ID (e.g., \"male-qn-qingse\", \"female-shaonv\")\nspeed: Speech speed (0.5-2)\nemotion: \"happy\", \"sad\", \"angry\", \"fearful\", \"disgusted\", \"surprised\", \"neutral\"\nformat: \"mp3\", \"wav\", \"pcm\", \"flac\"\nlanguageBoost: Enhance recognition for specific languages/dialects\nCantonese: \"Chinese,Yue\" or \"Chinese\"\nMandarin: \"Chinese\" or \"Chinese,Mandarin\"\nEnglish: \"English\"\nAlways include this when generating Cantonese audio!\ngenerate_video\nprompt: Video description\nmodel: \"T2V-01\", \"T2V-01-Director\", \"I2V-01\", \"I2V-01-Director\", \"I2V-01-live\", \"MiniMax-Hailuo-02\"\nduration: 6 or 10 (for MiniMax-Hailuo-02)\nresolution: \"768P\", \"1080P\"\nOptimization & Troubleshooting\nTimeout Management: Video generation can take significant time (up to 20-30 minutes for high-quality 10s clips). Always pass a large --timeout value (e.g., --timeout 1800000) to mcporter to prevent early termination.\nGateway Turn Limit: Most OpenClaw profiles have a 10-minute turn timeout (600000ms). To avoid being killed by the gateway, ALWAYS run generate_video with background: true or inside a background process.\nModel Choice: Use MiniMax-Hailuo-02 for higher quality 10-second videos.\nError Handling\n\nIf you get 403 Forbidden when sending to Telegram:\n\nMake sure you're using the FULL URL with query string\nThe token (Signature) expires - regenerate if needed\nNotes\nMiniMax MCP must be configured with MINIMAX_RESOURCE_MODE=url in mcporter config\nGenerated media URLs include authentication tokens that expire\nAlways use the complete URL returned by MCP calls\nCantonese (廣東話) Tips\n\nWhen generating Cantonese audio:\n\nUse voice ID from Cantonese category (e.g., \"Cantonese_PlayfulMan\", \"Cantonese_CuteGirl\")\nAlways add: languageBoost:\"Chinese,Yue\" or languageBoost:\"Chinese\"\nExample:\nmcporter call minimax-mcp.text_to_audio text:\"新年快樂\" voiceId:\"Cantonese_PlayfulMan\" languageBoost:\"Chinese,Yue\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/hoyin258/minimax-to-telegram",
    "publisherUrl": "https://clawhub.ai/hoyin258/minimax-to-telegram",
    "owner": "hoyin258",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/minimax-to-telegram",
    "downloadUrl": "https://openagent3.xyz/downloads/minimax-to-telegram",
    "agentUrl": "https://openagent3.xyz/skills/minimax-to-telegram/agent",
    "manifestUrl": "https://openagent3.xyz/skills/minimax-to-telegram/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/minimax-to-telegram/agent.md"
  }
}