Mcp Media Url Transcriber

com.mambabuilt由 mambabuilt.com 发布v1.0.0更新于 Nov 8, 2026

Transcribe direct audio and video file links on your own speech to text API key

已验证STDIO仅桌面媒体与设计AI 与机器学习

概览

AI 生成的概览

通过 Apify actor，使用你自己的 Deepgram、AssemblyAI、Groq 或 OpenAI 密钥，把直链音视频文件转写为文字。

可以做什么
  • 用选定的语音转文字服务和你自己的 API 密钥转写直链音视频文件
  • 每个文件返回一行结果，包含转写文本、带时间戳的分段、识别语言和时长
  • 可选标注说话人（说话人分离），并指定模型或语言代码
  • 无密钥时可免费检查最多 3 个文件，并拒绝 YouTube、TikTok 等平台页面
适用场景
当你手上有播客、通话录音或访谈等无需登录的直链文件，并希望在助手内直接得到转写结果、而不必自建流程时适用。也适合在付费转写前先免费确认链接是否可读取。
运行要求
以 npm 包形式通过 npx 在本机运行，需要 Node.js 18 或更高版本。需要 Apify 账号，并设置环境变量 APIFY_TOKEN。转写需在调用时提供你自己的服务商 API 密钥（Deepgram、AssemblyAI、Groq 或 OpenAI）；OpenAI 仅接受不超过 25 MB 的文件。需要访问 Apify 和服务商的网络。
安装前请注意
服务商 API 密钥作为工具参数传入，由 Apify 加密存储后仅发送给该服务商，应视为可计费的机密。费用真实存在：你直接向服务商付费，并按媒体分钟数和每次运行启动向 Apify 付费；max_charge_usd 只限制该 actor 的费用，不限制服务商账单。说话人分离可能作为附加项计费。媒体文件会发送给第三方服务。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp Media Url Transcriber，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Desktop only，通过 STDIO。 STDIO 服务会启动本地进程，因此需要 SourceWeft 桌面宿主。

其他 MCP 客户端

参照 仓库 中的启动说明。

README

Media URL Transcriber MCP Server

[npm version] [license]

An MCP server for the Mamba Labs Media URL Transcriber actor on Apify. Turn media file links into transcripts on your own provider key.

What's Inside

What it does

Give direct audio or video file links and your own Deepgram, AssemblyAI, Groq, or OpenAI key. The actor sends each file to that provider and returns one row per file with the transcript, timestamped segments, language, and duration. You pay your provider directly and pay this actor per media minute. It does not download from platforms such as YouTube or TikTok.

All of the work runs on Apify. This package is a thin client that starts the actor run, waits for it, and hands back the dataset rows.

Quick start

You need Node.js 18 or newer and an Apify account with an API token.

Add this to your Claude Desktop config (claude_desktop_config.json), Cursor, or any MCP client:

json
{  "mcpServers": {    "mamba-media-url-transcriber": {      "command": "npx",      "args": [        "-y",        "@mambalabsdev/mcp-media-url-transcriber"      ],      "env": {        "APIFY_TOKEN": "your-apify-token"      }    }  }}

Restart the client. The transcribe_media_urls tool appears.

Prerequisites

Example prompts

  • "Transcribe this podcast episode file on my Deepgram key."
  • "Turn these 10 recorded call files into text with speaker labels."
  • "Check whether these media links can be read before I transcribe them."

Tool

transcribe_media_urls. One tool. Example arguments:

json
{  "media_urls": [    "https://dpgr.am/spacewalk.wav"  ],  "provider": "deepgram"}

Inputs

Every buyer facing input of the actor. Omitted inputs take the actor's own defaults.

InputTypeRequiredDescription
media_urlsarraynoDirect links to audio or video files (mp3, wav, m4a, mp4, and others) that answer without a login. Platform pages such as YouTube, TikTok, Instagram, Vimeo, or Spotify are refused with a free row. In Clay, put the column inside a one item list.
providerstringnoWhose API transcribes the file, on your key: deepgram (default), assemblyai, groq, or openai. openai takes files up to 25 MB; the others read the URL.
api_keystringnoYour own key for the provider above. It is stored encrypted by Apify, sent only to that provider, and never written to a row or a log. With no key the run checks up to 3 files and transcribes nothing, for free.
modelstringnoOptional. The provider's model name. Defaults: deepgram nova-3, assemblyai its own default, groq whisper-large-v3-turbo, openai whisper-1 (the only one accepted there).
languagestringnoOptional. A language code such as en or de. Empty lets deepgram and assemblyai detect it; whisper models detect it on their own.
diarizebooleannoyes or no (default no). Labels who spoke each segment. deepgram and assemblyai only; your provider may bill it as an add on.
include_segmentsbooleannoyes (default) or no. Adds a list of segments with start and end seconds to each row.
max_charge_usdstringnoOptional. No new file starts once this is used up. A transcript your provider already billed is still delivered, charged up to this amount, and the run then stops. It limits this actor's charge, not your provider's bill.

Pricing

Pay per event on Apify, billed to your Apify account. Prices in USD.

EventFree planBronzeSilverGold
media-minute, one minute of media transcribed, rounded up per file$0.005$0.00475$0.0045$0.00425
apify-actor-start, per run start$0.003$0.003$0.003$0.003

Refused, failed, and silent files, media checks with no key, and refused input are free. Mamba Labs pays the platform costs of the run. Mamba Labs pays the platform costs of the run, Apify proxy traffic included.

Full actor documentation

apify.com/mambalabs/media-url-transcriber

License

MIT. See LICENSE.

来源：README.md，提交 6b9cbc2

工具

1

transcribe_media_urls

Transcribe media file URLs on your own key

Give direct audio or video file links and your own Deepgram, AssemblyAI, Groq, or OpenAI key. Returns one row per file with the transcript, timestamped segments, language, and duration. Platform pages such as YouTube are refused. With no key it checks up to 3 files for free. Pay per event on Apify: 0.005 USD per media minute, plus your provider's bill.

输入参数modelapi_keydiarizelanguageprovidermedia_urlsmax_charge_usdinclude_segments

版本历史

1
  1. v1.0.0最新Nov 8, 2026

评分

已满足适用检查项的 90%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通25 分
  • 已声明认证方式10 分

    请在注册中心条目中声明凭据请求头，或保持端点能够响应探测，以便判定其认证方式。

  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分