whisper-windows-mcp

A Windows-native MCP (Model Context Protocol) server that lets Claude Desktop transcribe audio and video files locally using whisper.cpp — with GPU acceleration, multilingual support, and batch processing. No internet connection required. No audio ever leaves your machine.

Why does this exist? The popular whisper-mcp package was built for macOS and assumes a Unix environment. It does not work on Windows. This package was written specifically for Windows users who want local AI transcription integrated with Claude Desktop.

---

What you can do with it

Once installed, you can say things like this directly in Claude Desktop:

• "Transcribe C:\Users\Me\Downloads\meeting.mp3"
• "Transcribe this folder of recordings and save each as a text file"
• "Generate Japanese and English subtitles for this video"
• "Start a batch transcription of everything in this folder"
• "How long will it take to transcribe these files?"
• "Check if GPU acceleration is working"

---

Requirements

1. Node.js 18 or later — nodejs.org
2. whisper.cpp binaries with Vulkan GPU support — see Step 1
3. A Whisper model file — see Step 2
4. FFmpeg — required for video files and non-WAV/MP3 audio

---

Step 1 — Install whisper.cpp binaries

Option A — Pre-built Vulkan release (recommended)

Download whisper-vulkan-win-x64.zip from the releases page.

This is a custom-compiled build with Vulkan GPU acceleration enabled. Works with AMD, NVIDIA, and Intel GPUs — no vendor-specific SDK required.

Extract to C:\whisper\Release\. You should end up with:

C:\whisper\Release\whisper-cli.exe
C:\whisper\Release\ggml-vulkan.dll
C:\whisper\Release\ggml.dll
C:\whisper\Release\ggml-base.dll
C:\whisper\Release\ggml-cpu.dll
C:\whisper\Release\whisper.dll

GPU acceleration is automatic — no additional configuration needed.

Option B — Build from source

Requires: Git, CMake, Visual Studio Build Tools 2022+ with "Desktop development with C++", Vulkan SDK from lunarg.com.

git clone https://github.com/ggml-org/whisper.cpp
cd whisper.cpp
cmake -B build -DGGML_VULKAN=ON -DCMAKE_BUILD_TYPE=Release
cmake --build build --config Release --target whisper-cli

Copy the binaries from build\bin\Release\ to C:\whisper\Release\.

Note: The official whisper.cpp Windows releases on GitHub do not include a Vulkan build. You must use the pre-built release above or compile from source with -DGGML_VULKAN=ON.

---

Step 2 — Download a Whisper model

Model	Size	Speed	Accuracy	Best for
ggml-tiny.en.bin	75 MB	Very fast	Basic	Quick tests
ggml-base.en.bin	142 MB	Fast	Good	Everyday English
ggml-small.en.bin	466 MB	Moderate	Better	Important recordings
ggml-medium.en.bin	1.5 GB	Fast on GPU	Very good	Best quality English
ggml-large-v3.bin	2.9 GB	Fast on GPU	Excellent	Multilingual, best accuracy

For English-only use: base.en or medium.en are the best starting points. For multilingual use (auto-detect, foreign language, translation): large-v3 is required. English-only models (*.en.bin) output [FOREIGN] on non-English audio and cannot be used for other languages.

Download from Hugging Face:

https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium.en.bin

Save to C:\whisper\models\.

---

Step 3 — Install FFmpeg

FFmpeg is required for video files and non-native audio formats.

Install via winget:

winget install ffmpeg

Or download from ffmpeg.org and add to your PATH.

Verify:

ffmpeg -version

---

Step 4 — Install this MCP server

npm install -g whisper-windows-mcp

---

Step 5 — Configure Claude Desktop

Open Claude Desktop → Settings → Developer → Edit Config.

Add the whisper entry:

{
  "mcpServers": {
    "whisper": {
      "command": "npx",
      "args": ["-y", "whisper-windows-mcp"],
      "env": {
        "WHISPER_CLI_PATH": "C:\\whisper\\Release\\whisper-cli.exe",
        "WHISPER_MODEL": "C:\\whisper\\models\\ggml-medium.en.bin"
      }
    }
  }
}

Config file location: C:\Users\YourName\AppData\Roaming\Claude\claude_desktop_config.json

Use double backslashes in all paths.

Save and fully restart Claude Desktop. You should see whisper listed with a green running badge in Settings → Developer.

---

Step 6 — Verify your setup

In Claude Desktop, ask:

"Check your whisper config"

Then:

"Check your system hardware"

This confirms your GPU is detected and Vulkan acceleration is active.

---

Available tools

transcribe_audio

Transcribe a single file. Supports blocking (default) or background mode for long files.

Parameter	Description
file_path	Absolute path to the file (required)
language	Language code (en, ja, es, etc.) or auto to detect. Default: en
output_format	text (default), timestamps, json, or srt
save_to_file	Save transcript as .txt next to the source file
background	Run as detached job — returns a job ID immediately. Use check_progress to monitor. Recommended for files over 10 minutes.
threads	CPU thread override

---

check_progress

Monitor a background transcription job started with transcribe_audio (background=true).

Returns elapsed time, last processed timestamp, percentage, and the full transcript when complete.

Parameter	Description
job_id	Job ID returned by transcribe_audio

---

start_batch

Automated sequential batch transcription of all untranscribed files in a folder. Sorts by duration (shortest first), processes one at a time as background jobs, validates each output.

Parameter	Description
folder_path	Path to folder (required)
language	Language code. Default: en
threads	CPU thread override

---

check_batch_progress

Monitor a running batch. Automatically advances to the next file when the current one finishes. Returns overall progress, current file with timestamp, ETA, and any failed files.

Parameter	Description
batch_id	Batch ID returned by start_batch

---

transcribe_batch (interactive)

Process files one at a time with a preview and confirmation before each. Useful when you want to review as you go.

Parameter	Description
folder_path	Path to folder (required)
file_index	Which file to process (1-based). Omit to list files first.
language	Language code. Default: en
recursive	Include subfolders

---

generate_subtitles

Generate SRT subtitle files. Supports automatic language detection and English translation output.

Parameter	Description
file_path	Path to file (required)
language	Language code or auto to detect. Default: en
translate_to_english	Also generate an English translation .en.srt. Only applies when source is not English.
threads	CPU thread override

When both native and translation are requested, two files are saved next to the source:

• filename.ja.srt — original language
• filename.en.srt — English translation

Whisper's built-in translation only translates to English. For other target languages, translate the .srt file contents separately.

---

analyze_media

Analyze files before committing to transcription. Returns duration, size, codec, and estimated transcription time on CPU and GPU. For folders, shows all files in a sortable table with transcription status.

Parameter	Description
path	Path to a single file or folder (required)
sort_by	For folders: duration (default), name, or size

---

check_config

Verify whisper-cli.exe, the model file, and FFmpeg are all accessible. Run this first if anything is failing.

---

check_system

Detect GPU hardware and verify Vulkan acceleration is available. Reports GPU name, VRAM, whether ggml-vulkan.dll is present, and recommends the best model size for your hardware.

---

Supported formats

Type	Formats
Native (no conversion)	mp3, wav
Video (auto-converted via FFmpeg)	mp4, mkv, avi, mov, webm, flv, wmv, m4v, ts, 3gp
Audio (auto-converted via FFmpeg)	m4a, ogg, flac

---

GPU acceleration

The pre-built Vulkan release enables GPU acceleration automatically. Tested on AMD Radeon RX Vega 56 (GCN 5th gen). Any GPU with Vulkan 1.0+ support should work, including NVIDIA and Intel Arc.

Performance comparison (medium.en model, ~5 minute audio file):

Hardware	Time
CPU only (Ryzen 7 2700x, 8 threads)	8–12 minutes
GPU (Vega 56 via Vulkan)	20–40 seconds

GPU utilization during transcription is typically 15–20%, dropping back to idle between files. CPU stays around 15%.

---

Multilingual support

Whisper can auto-detect the spoken language and transcribe in that language. The built-in translation model translates to English only.

For best multilingual accuracy, use the large-v3 model. English-specific models (*.en.bin) cannot detect or transcribe other languages.

Example — foreign language video with subtitles:

1. Ask Claude to generate subtitles with language=auto and translate_to_english=true
2. Whisper detects the language and generates a native-language SRT
3. A second pass generates an English translation SRT
4. Load either file in VLC via Subtitle → Add Subtitle File

---

Designed for free-tier users

This tool is built to minimize Claude API interactions. The entire transcription workflow — scan, analyze, queue, run, validate — is designed to require as few Claude interactions as possible. Heavy lifting is done locally on your machine.

---

Optional environment variables

Variable	Description
WHISPER_CLI_PATH	Path to whisper-cli.exe (required)
WHISPER_MODEL	Path to model .bin file (required)
WHISPER_THREADS	CPU thread count override
FFMPEG_PATH	Path to ffmpeg if not in system PATH

---

Troubleshooting

See TROUBLESHOOTING.md for detailed solutions.

Quick checklist:

• Paths in config use double backslashes (C:\\whisper\\...)
• whisper-cli.exe exists at the configured path
• Model .bin file exists at the configured path
• FFmpeg is installed and in PATH (ffmpeg -version works)
• Claude Desktop was fully restarted after editing config
• Whisper shows running in Settings → Developer

---

License

MIT

---

Contributing

Pull requests welcome. See ROADMAP.md for planned features.

If you've tested GPU acceleration on hardware not listed above, please open an issue with your results — GPU model, VRAM, model size, and observed throughput.