Name: Whissle MCP Server
Author: WhissleAI

LABSCO SUMMARY

Every tool that reaches Whissle carries its own cost warning, with the instruction to run only when the user explicitly asks — restraint written into the descriptions rather than left to the caller.

speech_to_text, diarize_speech, translate_text and summarize_text each repeat that warning; list_asr_models is the tool you can call freely to see what you would be paying for. The audio side works on local paths and writes its result back to disk rather than returning it inline, so a transcript is a file you then have to open — worth knowing before wiring this into anything that expects text in the response. translate_text and summarize_text take text directly, which makes them usable on their own and not only on what the transcriber just produced.

What it is

A Whissle client for spoken and written language: transcription, speaker diarization, translation and summarisation, plus a listing of the ASR models available to you.

What you get

speech_to_text transcribes the file at audio_file_path using the ASR model named in model_name, and can return timestamps.
boosted_lm_words and boosted_lm_score bias recognition toward terms you supply, so names and domain jargon survive into the transcript.
diarize_speech produces the same transcript with speaker labels attached, bounded by max_speakers.
Transcripts are written out as a text file to a directory you name, or to $HOME/Desktop when you name none.
translate_text moves text between language codes given as source_language and target_language, such as en to es.
summarize_text condenses the text in content using the model named in model_name, following any instruction you attach.
list_asr_models reports the available ASR models and what each can do.

Requirements

A Whissle auth token, supplied as WHISSLE_AUTH_TOKEN (the README says to get one from your administrator), and Python 3.8 or higher. Audio has to be a file the server can open at the path you pass as audio_file_path.

Setup effort

Build from source — git clone https://github.com/WhissleAI/whissle-mcp

See installation options

USE CASES

01

Getting a usable transcript out of a recorded interview

Check which ASR models are available, then transcribe the file with the vocabulary that matters to you boosted so names come through.

list_asr_modelsspeech_to_text

02

Working out who said what in a meeting recording

Transcribe with speaker labels attached, capping how many voices the model should try to separate.

diarize_speech

03

Turning a long transcript into something a reader will finish

Summarise the text with an instruction that says what the summary is for, rather than accepting a generic condensation.

summarize_text

04

Reading a document that arrived in the wrong language

Translate between language codes when the source and target languages are already known.

translate_text

5 tools

Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.

`diarize_speech`

Convert speech to text with speaker diarization and save the output text file to a given directory. Directory is optional, if not provided, the output file will be saved to $HOME/Desktop.

⚠️ COST WARNING: This tool makes an API call to Whissle which may incur costs. Only use when explicitly requested by the user.

Args: audio_file_path (str): Path to the audio file to transcribe model_name (str, optional): The name of the ASR model to use. Defaults to "en-NER" max_speakers (int, optional): Maximum number of speakers to identify boosted_lm_words (List[str], optional): Words to boost in recognition boosted_lm_score (int, optional): Score for boosted words (0-100) output_directory (str, optional): Directory where files should be saved. Defaults to $HOME/Desktop if not provided.

Returns: TextContent with the diarized transcription and path to the output file.

BEFORE YOU INSTALL

What to know first

Tools you get

5 tools when we connected. speech_to_text, diarize_speech, translate_text and summarize_text call the paid Whissle API; list_asr_models is free. Audio files are limited to 25 MB in WAV, MP3, OGG, FLAC or M4A.

Requires

Python 3.8
WHISSLE_AUTH_TOKEN in your environment

Where it runs

The documented client runs the server on your machine.

CONTEXT COST

Light Standing cost

Rated by the size of the 5 tool definitions that ride along on every turn, not by how many there are

INSTALLATION

Connect your client

You clone this one yourself.

Server setup

Clone the repository:

TERMINAL

git clone https://github.com/WhissleAI/whissle-mcp
cd whissle-mcp

Create and activate a virtual environment:

TERMINAL

python -m venv venv
source venv/bin/activate # On Windows, use: venv\Scripts\activate

Install the required packages:

TERMINAL

pip install -e .

MCP Clients

Claude Desktop

CLAUDE DESKTOP · JSON

{
  "mcpServers": {
    "Whissle": {
      "command": "<YOUR_PATH_TO_VENV>/bin/python",
      "args": [
        "<YOUR_PATH_TO_WHISSLE_MCP>/server.py"
      ],
      "env": {
        "WHISSLE_AUTH_TOKEN": "<YOUR_WHISSLE_AUTH_TOKEN>"
      }
    }
  }
}

Whissle MCP Server

Every tool that reaches Whissle carries its own cost warning, with the instruction to run only when the user explicitly asks — restraint written into the descriptions rather than left to the caller.

What it is

What you get

Requirements

Setup effort

Getting a usable transcript out of a recorded interview

Working out who said what in a meeting recording

Turning a long transcript into something a reader will finish

Reading a document that arrived in the wrong language

5 tools

`diarize_speech`

`list_asr_models`

`speech_to_text`

`summarize_text`

`translate_text`

What to know first

Tools you get

Requires

Where it runs

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Desktop

Whissle MCP Server

Every tool that reaches Whissle carries its own cost warning, with the instruction to run only when the user explicitly asks — restraint written into the descriptions rather than left to the caller.

What it is

What you get

Requirements

Setup effort

Getting a usable transcript out of a recorded interview

Working out who said what in a meeting recording

Turning a long transcript into something a reader will finish

Reading a document that arrived in the wrong language

5 tools

diarize_speech

list_asr_models

speech_to_text

summarize_text

translate_text

What to know first

Tools you get

Requires

Where it runs

Light Standing cost

Connect your client

Server setup

MCP Clients

Claude Desktop

Same category

Scriptivox

TranscriptionTools

OpenAI Speech-to-Text

dTelecom STT

`diarize_speech`

`list_asr_models`

`speech_to_text`

`summarize_text`

`translate_text`