MoneyTools Transcripts

STT + SRT/VTT; 3-hour async jobs; dTelecom-compatible file API; x402 $0.005/min, no prepaid credits

使うべきか

品質と安全性

A
説明の品質
100%
スキーマの完全性
83%
命名の品質
80%
ポイズニングのリスク
100%
権限の一致
80%
プロトコルへの準拠
100%

検出事項(2)

  • LOWTool 'speech_upload_url' suggests web access but openWorldHint=falsespeech_upload_url 内
  • LOWTool 'speech_job_upload_url' suggests web access but openWorldHint=falsespeech_job_upload_url 内

ツール定義とプロトコルへの準拠に関する自動分析に基づいています。

コンテキストコスト

~1,453トークン数(ツール定義)
~1.3 KB一般的なレスポンスサイズ
注意への影響は中程度(128k コンテキストの 1.14%)

これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。

インストール

ワンクリックインストール

これを `claude_desktop_config.json` ファイルに追加してください:

{
  "mcpServers": {
    "transcripts": {
      "url": "https://speech.moneytools.dev/mcp"
    }
  }
}

リモートエンドポイント

https://speech.moneytools.dev/mcpstreamable-http

できること

ツール一覧

ツール(7)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢speech_report

Paid live status snapshot: capacity remaining today, price table, billing rule, capabilities. 0.005 USDC via x402 over MCP (unpaid → PaymentRequired). Free quote remains at speech_quote / GET /v1/speech/quote.

入力スキーマ

{
  "type": "object",
  "properties": {}
}
🟢speech_quote(minutes, seconds, bytes, url)

Free: estimate the exact x402 price from minutes, seconds, bytes, or an audio URL (HEAD). Billing uses max(declared, parsed duration, 16 kbps size floor).

入力スキーマ

{
  "type": "object",
  "properties": {
    "minutes": {
      "type": "number",
      "description": "Audio duration in minutes (hint only; never underprices alone)."
    },
    "seconds": {
      "type": "number",
      "description": "Audio duration in seconds (hint only)."
    },
    "bytes": {
      "type": "number",
      "description": "Audio file size in bytes (16 kbps floor used for pricing)."
    },
    "url": {
      "type": "string",
      "description": "HTTPS audio URL; we HEAD for Content-Length (SSRF-protected)."
    }
  }
}
🟢speech_upload_url(filename, bytes, contentType)

Free: mint a short-lived (15 min), single-use PUT URL for local media. PUT the file via plain HTTP (not MCP), then pass upload_id to speech_transcribe. Size cap matches MaxBytes; rate-limited per client. Not a public file host — bytes are deleted after transcription or expiry.

入力スキーマ

{
  "type": "object",
  "properties": {
    "filename": {
      "type": "string",
      "description": "Optional original filename (metadata only)."
    },
    "bytes": {
      "type": "number",
      "description": "Optional declared size hint; must not exceed MaxBytes."
    },
    "contentType": {
      "type": "string",
      "description": "Optional Content-Type to recommend on PUT (audio/* or video/*)."
    }
  }
}
🟡speech_transcribe(url, uploadId, audioBase64, language, summary, ...)

Generate a value-added transcript with timestamped segments, SRT/VTT, language detection, word count and duration (optional summary). 0.005 USDC/started minute (min 0.005); 3 free/day. Pass url, upload_id (from speech_upload_url), or audioBase64 — WAV/MP3/M4A/MP4/WebM/OGG/FLAC you have the right to process. Platform pages refused. Max 10 min / 25 MB. Price = max(declared, parsed, 16 kbps floor).

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "HTTPS direct media file URL you have the right to process (audio/* or video/*; MP3/M4A/MP4/WebM/WAV/…). Not a YouTube/Instagram/TikTok/Facebook/X/Vimeo page."
    },
    "uploadId": {
      "type": "string",
      "description": "upload_id from speech_upload_url after a successful PUT (single-use)."
    },
    "audioBase64": {
      "type": "string",
      "description": "Base64-encoded audio bytes (alternative to url/uploadId)."
    },
    "language": {
      "type": "string",
      "description": "Optional language hint (e.g. en, zh). If omitted we detect language."
    },
    "summary": {
      "type": "boolean",
      "description": "If true, include a short 1–3 sentence summary."
    },
    "durationSeconds": {
      "type": "number",
      "description": "Declared duration hint in seconds (cannot underprice; we parse the file)."
    },
    "minutes": {
      "type": "number",
      "description": "Declared duration hint in minutes."
    }
  }
}
🟡speech_job_upload_url(bytes, contentType, language, summary, webhook, ...)

Free: mint a signed single-use PUT URL for a long file (up to 100 MB / 180 min; MP3/WAV are segmented). PUT via plain HTTP; the PUT response carries the exact price. Then speech_job_submit with uploadId.

入力スキーマ

{
  "type": "object",
  "properties": {
    "bytes": {
      "type": "number",
      "description": "Optional file size hint in bytes."
    },
    "contentType": {
      "type": "string",
      "description": "Content-Type to use on PUT (audio/* or video/*)."
    },
    "language": {
      "type": "string",
      "description": "Optional language hint (e.g. en, zh)."
    },
    "summary": {
      "type": "boolean",
      "description": "Include a short summary when done."
    },
    "webhook": {
      "type": "string",
      "description": "Optional public https URL for a signed job.done callback."
    },
    "durationSeconds": {
      "type": "number",
      "description": "Declared duration hint (can only raise the price)."
    }
  }
}
🟡speech_job_submit(url, uploadId, language, summary, webhook, ...)

Submit a long audio file (url or uploadId) as an async job: 0.005 USDC per started minute (exact, x402 Base USDC), up to 180 min. Without payment returns PaymentRequired with the exact price; pay via _meta["x402/payment"]. First segment is transcribed before settlement; then poll speech_job_status or get a signed webhook.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "description": "HTTPS direct media URL you have the right to process (not a platform page)."
    },
    "uploadId": {
      "type": "string",
      "description": "job_… id from speech_job_upload_url after the PUT."
    },
    "language": {
      "type": "string",
      "description": "Optional language hint (e.g. en, zh)."
    },
    "summary": {
      "type": "boolean",
      "description": "Include a short summary when done."
    },
    "webhook": {
      "type": "string",
      "description": "Optional public https URL for a signed job.done callback."
    },
    "durationSeconds": {
      "type": "number",
      "description": "Declared duration hint (can only raise the price)."
    }
  }
}
🟢speech_job_status(jobId, jobToken, format)

Free: status, progress and (when done) transcript, segments, SRT/VTT of an async job. Needs jobId + jobToken (shown once at submit). format=srt|vtt|txt returns that text only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "jobId": {
      "type": "string",
      "description": "job_… id from speech_job_submit."
    },
    "jobToken": {
      "type": "string",
      "description": "jt_… token returned once at submit."
    },
    "format": {
      "type": "string",
      "enum": [
        "json",
        "srt",
        "vtt",
        "txt"
      ],
      "description": "json (default) or a subtitle/text format."
    }
  },
  "required": [
    "jobId"
  ]
}

コミュニティ

このサーバーを評価する

エビデンス

最近の観測

検証済みバージョンは記録されていませんツール 7 件