mcpcost

io.github.cykk/audio-transcription-mcp

Audio Transcription MCP

Is the Audio Transcription MCP server down? No. It answered initialize and tools/list in the probe of 2026-11-11.

Transcribe local audio and video using Whisper or the OpenAI API.

alive probed 2026-11-15 · unchanged since 2026-11-11

1tools
363tokens in Claude Opus 5.5
0.2 %of Claude's 200k window
0.1×the median server
1.3 sto initialize
4 msto list tools
Run it
uvx audio-transcription-mcp@0.1.0 (stdio, probed in a container with the network off)
Host
pypi.org
Reports itself as
Audio Transcription MCP 1.30.0
Capabilities
experimental, prompts, resources, tools
Instructions
none
Of a 1M window
<0.1 % of a 1M context window
Count
363 tokens in Claude Opus 5.5, exact, measured 2026-11-11. With the Claude Code prefix mcp__…__ on each tool name: 378. The o200k_base estimate is 201. Counted again when the tool definitions change. Method.
Repository
https://github.com/cykk/audio-transcription-mcp
Website
https://mp3totext.io/
Registry
active, updated 2026-11-11 · registry entry

Most expensive tools

The Claude column scales the o200k estimate of each tool by this server's ratio of exact to estimate, 1.81×.

Tool≈ Claude tokenso200k estimateShare of this server
transcribe_file363201100 %

Compare this server with others.

More servers

Other registry entries on pypi.org, the ones next to this name; all of them.

Servers that mention transcription.

Badge for the README

mcpcost: alive

The result of the latest probe, the tool count and the token cost. The feed has an entry for every probe that changed them.

Atom feed

A mail when this server changes

Stops answering, comes back, tool set or cost changes. One confirmation mail first, a stop link in every mail.

For the publisher