Whisper Transcribe MCP Server

by zahirinatzuke Your server? Claim it

local only

Whisper Transcribe runs on your own machine — the client starts it, so there is no endpoint to ping. 88 installs a week from pypi. Last commit 24 Jul 2026.

Transcribe audio locally with faster-whisper or through the OpenAI Whisper API.

Installs per day peak 59 · avg 19 · -33% w/w

a month agotoday

Installs / week

pypi · whisper-transcribe-mcp

Stars

0 open issues

24 Jul 2026

Last commit

0 releases in 90 days

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Whisper Transcribe every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add whisper-transcribe-mcp -- uvx whisper-transcribe-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "whisper-transcribe-mcp": {
      "args": [
        "whisper-transcribe-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.whisper-transcribe-mcp]
command = "uvx"
args = ["whisper-transcribe-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "whisper-transcribe-mcp": {
      "args": [
        "whisper-transcribe-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "whisper-transcribe-mcp": {
      "args": [
        "whisper-transcribe-mcp"
      ],
      "command": "uvx"
    }
  }
}

This one needs environment variables set before it will start: OPENAI_API_KEY (OpenAI API key. Enables the cloud backend and optional GPT post-processing.), WHISPER_MODEL (Default faster-whisper model size when using the local backend.). The author declared them in the registry entry; get the values from the project itself.

Alternatives to Whisper Transcribe

same job, measured the same way

Whisper MCP

by jwulff

Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.

124 installs/wk local only

SpeechWeave

by speechweave

Transcribe local files and URLs with SpeechWeave's OpenAI-compatible API.

58 installs/wk local only

CrispASR Agent Transcriber

by emiyakatuz

Transcribe and understand local audio/video with CrispASR and local models only.

138 installs/wk local only

MCP Transcribe

by ipv6

MCP-Transcribe server allows LLMs to interact with the text content of audio/video files

local only

Macwhisper MCP Server

by docdyhr

MacWhisper transcription for Claude Desktop. Fully local, no cloud, audio stays on your Mac.

116 installs/wk local only

FunASR

by modelscope

Transcribe local audio with FunASR and SenseVoice using private, on-device inference.

local only

Edict

by edict

Search your dictation transcripts and transcribe audio or video on-device, with speaker labels.

local only

Openapi Lint

by cedrickouma

MCP server (stdio): lint OpenAPI specs with Spectral via the AgentForge API

25 installs/wk answering

Whisper Transcribe — questions

Answers built from our own checks of this server.

Why is there no uptime for Whisper Transcribe?

Whisper Transcribe runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package whisper-transcribe-mcp was installed 88 times last week.

How do I connect Whisper Transcribe?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls whisper-transcribe-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Whisper Transcribe?

The pypi package whisper-transcribe-mcp was installed 88 times in the last week. Week over week that is -33%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Whisper Transcribe open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.