babelscribe — Claude Code MCP server: what it does, how to install
Runs offline speech recognition and builds subtitles locally on your GPU. Lets coding agents transcribe local audio and video files across 99 languages without cloud APIs.
claude mcp add babelscribe -- uvx babelscribeWhat babelscribe does
The server wraps whisper.cpp to deliver transcription and subtitle generation directly on local hardware. It runs on AMD, NVIDIA, Intel, and Apple Silicon chips using Vulkan, CUDA, or Metal, with a CPU fallback when no GPU is present. Because it fetches precompiled whisper-cli binaries automatically, you avoid building native drivers manually.
Four tools are exposed to the AI model: transcribe for making subtitle and text files, find_media to locate recent media in user directories, list_devices, and list_languages_and_models. In Codex, default timeout limits cause jobs to drop during the initial model fetch. You must raise tool_timeout_sec to 3600 in your Codex configuration file before running large files.
What it helps with
- generate SRT or VTT subtitles from video recordings
- transcribe speech locally without uploading media to third-party clouds
- locate the newest video in standard system folders automatically
- run Whisper models on AMD graphics cards using Vulkan
Example prompts for the agent
- Find the newest recording in my Downloads folder and generate subtitles for it.
- Transcribe interview.mp4 and write the text transcript next to the file.
- List all available hardware devices for speech processing.
How to install babelscribe
Platform CLI
claude mcp add babelscribe -- uvx babelscribeuvx runs the command named after the package; if the README names another one, use uvx --from babelscribe <command>
Platform CLI
codex mcp add babelscribe -- uvx babelscribeuvx runs the command named after the package; if the README names another one, use uvx --from babelscribe <command>
Config file
{
"mcpServers": {
"babelscribe": {
"command": "uvx",
"args": [
"babelscribe"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from babelscribe <command>
Config file
{
"servers": {
"babelscribe": {
"type": "stdio",
"command": "uvx",
"args": [
"babelscribe"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from babelscribe <command>
Platform CLI
gemini mcp add babelscribe uvx babelscribeuvx runs the command named after the package; if the README names another one, use uvx --from babelscribe <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about babelscribe
How to install babelscribe in Claude Code?
Run claude mcp add babelscribe -- uvx babelscribe in your terminal. uv pulls the package and launches the server automatically.
What does babelscribe do?
It enables local speech-to-text processing on your own hardware via whisper.cpp. The server handles transcription and subtitle generation in 99 languages without sending audio files off your machine.
Which graphics cards are supported?
It runs on AMD, NVIDIA, and Intel hardware via Vulkan, uses Metal on Apple Silicon, and supports CUDA on Linux. A CPU mode is also available if your computer lacks a dedicated graphics chip.
