TranscriptLab

Turn YouTube videos and audio or video files into searchable, exportable transcripts.

使うべきか

品質と安全性

A
説明の品質
99%
スキーマの完全性
89%
命名の品質
71%
ポイズニングのリスク
100%
権限の一致
100%
プロトコルへの準拠
100%

検出事項(10)

  • LOWTool 'transcriptlab_list_job_items' description lacks action verbtranscriptlab_list_job_items 内
  • LOWTool 'transcriptlab_retrieve_transcript' name length outside 3-30 rangetranscriptlab_retrieve_transcript 内
  • LOWTool 'transcriptlab_discover_captions' name length outside 3-30 rangetranscriptlab_discover_captions 内
  • LOWTool 'transcriptlab_search_transcript' name length outside 3-30 rangetranscriptlab_search_transcript 内
  • LOWTool 'transcriptlab_create_checkout_link' name length outside 3-30 rangetranscriptlab_create_checkout_link 内
  • LOWTool 'transcriptlab_begin_audio_upload' name length outside 3-30 rangetranscriptlab_begin_audio_upload 内
  • LOWTool 'transcriptlab_start_audio_transcription' name length outside 3-30 rangetranscriptlab_start_audio_transcription 内
  • LOWTool 'transcriptlab_read_audio_transcript' name length outside 3-30 rangetranscriptlab_read_audio_transcript 内
  • LOWTool 'transcriptlab_transcribe_media_url' name length outside 3-30 rangetranscriptlab_transcribe_media_url 内
  • LOWTool 'transcriptlab_get_speech_transcript' name length outside 3-30 rangetranscriptlab_get_speech_transcript 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

~4,264トークン数(ツール定義)
~1.2 KB一般的なレスポンスサイズ
注意への影響は大きい(128k コンテキストの 3.33%)

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": {
    "transcriptlab": {
      "url": "https://api.transcriptlab.dev/mcp"
    }
  }
}

リモートエンドポイント

https://api.transcriptlab.dev/mcpstreamable-http

できること

ツール一覧

ツール(20)

🟢 読み取り専用🟡 書き込み🔴 削除⚪ 不明
🟢transcriptlab_get_transcript(url, lang, translate, type, format, ...)

Get a YouTube transcript from existing captions. Use when the user gives a YouTube link or video ID and wants the transcript. Returns the transcript, or a job id when the request outlives the synchronous window: if a job comes back, poll transcriptlab_get_job_status, then read the text with transcriptlab_retrieve_transcript. The first delivery of each transcript variant can spend credits; later deliveries of that variant are free. Captions only: when the user asks which caption tracks exist use transcriptlab_discover_captions; when the video has no captions, or the source is an attached file or a direct media link, use transcriptlab_transcribe_file or transcriptlab_transcribe_media_url.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2048,
      "description": "YouTube video URL or 11-character video ID."
    },
    "lang": {
      "type": "string",
      "pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
      "description": "Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language."
    },
    "translate": {
      "type": "string",
      "pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
      "description": "Translate captions to this language when available."
    },
    "type": {
      "type": "string",
      "enum": [
        "any",
        "manual",
        "generated"
      ],
      "description": "Caption track type; defaults to any."
    },
    "format": {
      "type": "string",
      "enum": [
        "json",
        "text",
        "srt",
        "vtt"
      ],
      "description": "Output format; defaults to json."
    },
    "metadata": {
      "type": "boolean",
      "description": "Include video metadata when available; defaults to true."
    },
    "also": {
      "type": "array",
      "items": {
        "type": "string",
        "enum": [
          "srt",
          "vtt",
          "text"
        ]
      },
      "maxItems": 3,
      "description": "Additional formats to include in a JSON response."
    },
    "cleanup": {
      "type": "boolean",
      "description": "Strip filler words and stray timestamps from the caption text."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢transcriptlab_retrieve_transcript(url, lang, translate, type, format, ...)

Read a YouTube transcript that is already published for this account, without starting a new fetch. Use it after transcriptlab_get_job_status reports a job done, or to re-open a variant that was delivered before. For a first request use transcriptlab_get_transcript instead. Reading an already delivered variant is free; a never-before-delivered variant can spend credits like the original request.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2048,
      "description": "YouTube video URL or 11-character video ID."
    },
    "lang": {
      "type": "string",
      "pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
      "description": "Caption language. Omit it to get the video's own language (recommended); set it only to request a specific language."
    },
    "translate": {
      "type": "string",
      "pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$",
      "description": "Translation target, if requested for the original fetch."
    },
    "type": {
      "type": "string",
      "enum": [
        "any",
        "manual",
        "generated"
      ]
    },
    "format": {
      "type": "string",
      "enum": [
        "json",
        "text",
        "srt",
        "vtt"
      ]
    },
    "metadata": {
      "type": "boolean"
    },
    "cleanup": {
      "type": "boolean"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢transcriptlab_discover_captions(url)

List the caption languages and track types (manual vs generated) available for a YouTube video. Use when the user asks which languages or subtitles a video has, or before transcriptlab_get_transcript when they want a specific language. Free in transcript credits, but subject to the account monthly discovery limit.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2048,
      "description": "YouTube video URL or 11-character video ID."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢transcriptlab_search_transcript(url, mode, terms, pattern, flags, ...)

Search, quote, or slice a transcript already delivered to this account. Use for "find the part where...", keyword or regex lookup, or paginating a long transcript into chunks. It never starts a fetch and never charges transcript credits, so it only works on a video already cached here: deliver it first with transcriptlab_get_transcript if it is not. mode chooses the behavior: keyword matches terms, regex matches a pattern, chunk returns sequential sections.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2048,
      "description": "YouTube video URL or 11-character video ID."
    },
    "mode": {
      "type": "string",
      "enum": [
        "keyword",
        "regex",
        "chunk"
      ],
      "description": "keyword matches terms, regex matches pattern, chunk returns sequential sections."
    },
    "terms": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 200
      },
      "maxItems": 50,
      "description": "Required in keyword mode."
    },
    "pattern": {
      "type": "string",
      "maxLength": 512,
      "description": "Required in regex mode."
    },
    "flags": {
      "type": "string",
      "maxLength": 8,
      "description": "Optional regular expression flags."
    },
    "case_sensitive": {
      "type": "boolean"
    },
    "context_chars": {
      "type": "integer",
      "minimum": 0,
      "maximum": 1000
    },
    "target_tokens": {
      "type": "integer",
      "minimum": 1,
      "maximum": 4096
    },
    "max_tokens": {
      "type": "integer",
      "minimum": 1,
      "maximum": 4096
    },
    "overlap_snippets": {
      "type": "integer",
      "minimum": 0,
      "maximum": 20
    },
    "lang": {
      "type": "string",
      "pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$"
    },
    "translate": {
      "type": "string",
      "pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$"
    },
    "type": {
      "type": "string",
      "enum": [
        "any",
        "manual",
        "generated"
      ]
    }
  },
  "required": [
    "url",
    "mode"
  ],
  "additionalProperties": false
}
🟢transcriptlab_get_job_status(job_id)

Check whether a transcript job from transcriptlab_get_transcript has finished. Use it when that tool returned a job_id instead of a transcript. Returns status only, delivers no transcript, and spends no credits; once it reports done, read the text with transcriptlab_retrieve_transcript.

入力スキーマ

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 128,
      "description": "Job id returned by transcriptlab_get_transcript."
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}
🟢transcriptlab_get_usage

Read the account plan, remaining credits, and current-period usage, plus upgrade options. Use when the user asks about cost, balance, or limits, or before a credit-spending request.

入力スキーマ

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟡transcriptlab_create_checkout_link(offer)

Create a hosted Dodo checkout link bound to the user's connected TranscriptLab account (no website sign-in required). Use when the user runs out of credits (insufficient_credits), asks to upgrade, or wants to buy more credits. Choose starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits). Always show the returned checkout_url verbatim as a clickable link.

入力スキーマ

{
  "type": "object",
  "properties": {
    "offer": {
      "type": "string",
      "enum": [
        "starter",
        "credit_pack"
      ],
      "description": "starter ($3.99/mo for 1,000 monthly credits) or credit_pack ($4.99 one-time for 1,000 non-expiring credits)."
    }
  },
  "required": [
    "offer"
  ],
  "additionalProperties": false
}
🟢transcriptlab_list_transcripts(search, limit, cursor)

List YouTube videos whose transcripts were already delivered to this account, most recent first. Use it to find or reopen an earlier transcript. It fetches nothing and delivers no transcript. When more results exist, page with the returned cursor.

入力スキーマ

{
  "type": "object",
  "properties": {
    "search": {
      "type": "string",
      "maxLength": 64,
      "description": "Optional video ID or title filter."
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100,
      "description": "Page size; defaults to the server default."
    },
    "cursor": {
      "type": "string",
      "maxLength": 2048,
      "description": "Opaque cursor returned by the previous page."
    }
  },
  "additionalProperties": false
}
🟢transcriptlab_mentions(query)

Composer at-mention search over the account’s transcript library, used to build the @TranscriptLab picker. App-facing only: the host calls it, it returns resource links rather than transcript text, and the model should not call it.

入力スキーマ

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "maxLength": 64,
      "description": "Typeahead text; may be empty."
    }
  },
  "additionalProperties": false
}
🟢transcriptlab_open_audio(file, diarize)

Entry point the host invokes when the user opens an audio or video file with this plugin: opens the uploader view and starts speech-to-text. You do not call this directly; for a file attached to the conversation use transcriptlab_transcribe_file.

入力スキーマ

{
  "type": "object",
  "properties": {
    "file": {
      "type": "object",
      "properties": {
        "name": {
          "type": "string"
        },
        "resourceUri": {
          "type": "string"
        }
      },
      "required": [
        "name",
        "resourceUri"
      ],
      "description": "Host-provided handle for the opened file."
    },
    "diarize": {
      "type": "boolean",
      "description": "Label speakers; defaults to false. Implies tier=premium and 10 credits per audio minute."
    }
  },
  "required": [
    "file"
  ],
  "additionalProperties": false
}
🟡transcriptlab_begin_audio_upload(name, bytes, content_type)

Create a signed direct-upload session for an opened audio file. App-facing only: the uploader view calls it, not the model.

入力スキーマ

{
  "type": "object",
  "properties": {
    "name": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256
    },
    "bytes": {
      "type": "integer",
      "minimum": 1,
      "maximum": 2000000000
    },
    "content_type": {
      "type": "string",
      "pattern": "^(audio|video)/",
      "description": "Media MIME type."
    }
  },
  "required": [
    "name",
    "bytes",
    "content_type"
  ],
  "additionalProperties": false
}
🟡transcriptlab_start_audio_transcription(upload_id, diarize, tier)

Finalize a signed upload and start speech-to-text on it. App-facing only: the uploader view calls it once the file is uploaded. Spends credits per audio minute.

入力スキーマ

{
  "type": "object",
  "properties": {
    "upload_id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 64
    },
    "diarize": {
      "type": "boolean",
      "description": "Label speakers; defaults to false. Implies tier=premium."
    },
    "tier": {
      "type": "string",
      "enum": [
        "normal",
        "premium",
        "auto"
      ],
      "description": "Speech model tier; defaults to auto (normal when available)."
    }
  },
  "required": [
    "upload_id"
  ],
  "additionalProperties": false
}
🟢transcriptlab_read_audio_transcript(upload_id, format)

Read the transcript of a file uploaded through the uploader view. A pending transcription reports 202; retry shortly. App-facing only.

入力スキーマ

{
  "type": "object",
  "properties": {
    "upload_id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 64
    },
    "format": {
      "type": "string",
      "enum": [
        "json",
        "text",
        "srt",
        "vtt"
      ]
    }
  },
  "required": [
    "upload_id"
  ],
  "additionalProperties": false
}
🟢transcriptlab_open(tab)

Open the TranscriptLab launcher view, where the user can work with transcripts visually and send one into the chat with "Discuss in chat". Use tab "upload" when a file needs the uploader: the user wants to pick a local audio or video file, the attached file is too large or could not be read by transcriptlab_transcribe_file, or that upload failed. Use "library" to reopen earlier transcripts, and "link" (the default) to paste a YouTube link. Also offer it when the user wants a transcript but has given no link or file.

入力スキーマ

{
  "type": "object",
  "properties": {
    "tab": {
      "type": "string",
      "enum": [
        "link",
        "upload",
        "library"
      ],
      "description": "Which launcher tab to show first; defaults to link."
    }
  },
  "additionalProperties": false
}
🟡transcriptlab_transcribe_file(file, diarize, tier)

Transcribe an audio or video file the user attached to this conversation, using speech-to-text (mp3, m4a, wav, mp4, webm and similar). Use it for an attached media file; YouTube links use transcriptlab_get_transcript instead. Spends credits per audio minute. Attachments up to 300 MB work here; larger files (up to 2 GB) use the launcher upload view. Stores the file, starts transcription, and returns an upload_id: poll transcriptlab_get_speech_transcript with it, waiting a few seconds between tries and stopping after about ten. Do not call this again for the same file. If it fails or the file is too large, call transcriptlab_open with tab "upload".

入力スキーマ

{
  "type": "object",
  "properties": {
    "file": {
      "type": "object",
      "description": "The attached media file.",
      "properties": {
        "download_url": {
          "type": "string",
          "maxLength": 4096
        },
        "file_id": {
          "type": "string",
          "maxLength": 256
        },
        "mime_type": {
          "type": "string",
          "maxLength": 256
        },
        "file_name": {
          "type": "string",
          "maxLength": 512
        }
      },
      "required": [
        "download_url",
        "file_id"
      ],
      "additionalProperties": false
    },
    "diarize": {
      "type": "boolean",
      "description": "Label speakers; defaults to false. Implies tier=premium."
    },
    "tier": {
      "type": "string",
      "enum": [
        "normal",
        "premium",
        "auto"
      ],
      "description": "Speech model tier; defaults to auto (normal when available)."
    }
  },
  "required": [
    "file"
  ],
  "additionalProperties": false
}
🟢transcriptlab_transcribe_media_url(url, diarize, tier)

Transcribe a public https link to an audio or video file with speech-to-text. Use it for a direct media URL (ending in .mp3, .m4a, .wav, .mp4, .webm and similar); not for YouTube or other web pages, which use transcriptlab_get_transcript. Spends credits per audio minute. Returns a media_id: poll transcriptlab_get_speech_transcript with it, waiting a few seconds between tries and stopping after about ten.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2048,
      "description": "Public https URL of an audio or video file."
    },
    "diarize": {
      "type": "boolean",
      "description": "Label speakers; defaults to false. Implies tier=premium."
    },
    "tier": {
      "type": "string",
      "enum": [
        "normal",
        "premium",
        "auto"
      ],
      "description": "Speech model tier; defaults to auto (normal when available)."
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢transcriptlab_get_speech_transcript(upload_id, media_id, format)

Read the speech-to-text transcript started by transcriptlab_transcribe_file (pass upload_id) or transcriptlab_transcribe_media_url (pass media_id). Pass exactly one id. While transcription runs it returns a pending result: wait a few seconds, back off, and stop after about ten tries; if it is still pending, tell the user the job is queued instead of looping. Reading does not start new work or add charges.

入力スキーマ

{
  "type": "object",
  "properties": {
    "upload_id": {
      "type": "string",
      "maxLength": 64,
      "description": "From transcriptlab_transcribe_file."
    },
    "media_id": {
      "type": "string",
      "maxLength": 64,
      "description": "From transcriptlab_transcribe_media_url."
    },
    "format": {
      "type": "string",
      "enum": [
        "json",
        "text",
        "srt",
        "vtt"
      ],
      "description": "Defaults to json."
    }
  },
  "additionalProperties": false
}
🟢transcriptlab_export_link(url, upload_id, format, lang)

Create a 10-minute signed download link (TXT, SRT, VTT, Markdown, or JSON) for a transcript the account already has, or for a transcribed upload. Call this when the user wants a file or a link to a file: hand them the returned url and say it expires in 10 minutes. Needs a signed-in connection. The launcher Download action calls it too, so a host that cannot start a download itself still gives the user the link.

入力スキーマ

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "maxLength": 2048,
      "description": "YouTube video URL or 11-character video ID."
    },
    "upload_id": {
      "type": "string",
      "maxLength": 64,
      "description": "Upload id of a transcribed file."
    },
    "format": {
      "type": "string",
      "enum": [
        "text",
        "srt",
        "vtt",
        "md",
        "json"
      ]
    },
    "lang": {
      "type": "string",
      "pattern": "^[a-z]{2,3}(-[a-z0-9]{2,8})*$"
    }
  },
  "additionalProperties": false
}
🟡transcriptlab_submit_batch(urls)

Queue a list of YouTube URLs as one batch job and return its job id. App-facing only. The plan caps how many URLs one job accepts.

入力スキーマ

{
  "type": "object",
  "properties": {
    "urls": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "maxItems": 500,
      "description": "YouTube URLs to transcribe."
    }
  },
  "required": [
    "urls"
  ],
  "additionalProperties": false
}
🟢transcriptlab_list_job_items(job_id, cursor, limit)

Return per-video results for a batch or channel job. App-facing only. Page with the returned cursor.

入力スキーマ

{
  "type": "object",
  "properties": {
    "job_id": {
      "type": "string",
      "minLength": 1,
      "maxLength": 64
    },
    "cursor": {
      "type": "string"
    },
    "limit": {
      "type": "integer",
      "minimum": 1,
      "maximum": 100
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

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 20 件