TranscribeText
Get YouTube video transcripts and transcribe TikTok videos to text from a link. No sign-up.
我该使用它吗
质量与安全性
基于对工具定义和协议合规性的自动分析。
上下文开销
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"transcribe": {
"url": "https://transcribetext.com/mcp"
}
}
}远程端点
https://transcribetext.com/mcpstreamable-http它能做什么
工具清单
工具（3）
🟢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.
输入模式
{
"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.
输入模式
{
"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.
输入模式
{
"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
}社区
证据