TranscribeText

Get YouTube video transcripts and transcribe TikTok videos to text from a link. No sign-up.

Should I use this

Quality & Safety

A
Description quality
100%
Schema completeness
100%
Naming quality
93%
Poisoning risk
100%
Permission match
100%
Protocol compliance
100%

Based on automated analysis of tool definitions and protocol compliance.

Context Cost

~545Tokens (tool definitions)
~1.1 KBTypical response size
Minimal attention impact (0.43% of 128k context)

This is the approximate number of tokens consumed each time the server's tools are loaded into a model's context. Higher counts reduce the attention available for other tasks.

Install

One-Click Install

Add this to your `claude_desktop_config.json` file:

{
  "mcpServers": {
    "transcribe": {
      "url": "https://transcribetext.com/mcp"
    }
  }
}

Remote endpoints

https://transcribetext.com/mcpstreamable-http

What it can do

Tool inventory

Tools (3)

🟢 Read-only🟡 Write🔴 Delete⚪ Unknown
🟢get_youtube_transcript(language, timestamps, url)

Get the transcript of a YouTube video from its link. Returns the captions YouTube has for the video (subtitles uploaded by the creator, or the auto-generated captions) as plain text, with the title, channel and the caption languages available. Does not work for videos without captions, or for private, members-only or age-restricted videos.

Input Schema

{
  "type": "object",
  "properties": {
    "language": {
      "description": "Language code of the captions to return, for example en, es or pt-BR. Defaults to the language spoken in the video.",
      "type": "string"
    },
    "timestamps": {
      "description": "Prefix every caption line with its start time, like [1:23]. Defaults to false.",
      "type": "boolean"
    },
    "url": {
      "description": "Link to a single YouTube video, for example https://www.youtube.com/watch?v=dQw4w9WgXcQ",
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢transcribe_tiktok_video(timestamps, url)

Transcribe the speech in a TikTok video to text from its link. The spoken language is detected automatically. Usually takes 20 to 60 seconds. Free use is limited per day and per video length; if the transcription is not finished when this call returns, it gives a job_id for get_transcription_result.

Input Schema

{
  "type": "object",
  "properties": {
    "timestamps": {
      "description": "Prefix every line with its start time, like [0:12]. Defaults to false.",
      "type": "boolean"
    },
    "url": {
      "description": "Link to a TikTok video, for example https://www.tiktok.com/@user/video/7300000000000000000 or a vm.tiktok.com share link.",
      "type": "string"
    }
  },
  "required": [
    "url"
  ],
  "additionalProperties": false
}
🟢get_transcription_result(job_id, timestamps)

Get the result of a transcription that transcribe_tiktok_video started but did not finish in time. Pass the job_id that call returned.

Input Schema

{
  "type": "object",
  "properties": {
    "job_id": {
      "description": "The job_id returned by transcribe_tiktok_video.",
      "type": "string"
    },
    "timestamps": {
      "description": "Prefix every line with its start time, like [0:12]. Defaults to false.",
      "type": "boolean"
    }
  },
  "required": [
    "job_id"
  ],
  "additionalProperties": false
}

Community

Rate this Server

Evidence

Recent observations

verifiedversion not recorded3 tools