---
slug: whisper-cpp
kind: runbook
status: docs-checked
sh: https://insidethemachine.ai/install/whisper-cpp.sh
ps1: null
json: https://insidethemachine.ai/install/whisper-cpp.json
page: https://insidethemachine.ai/setups/whisper-cpp
---

# Install: whisper.cpp

Local speech-to-text with Metal GPU acceleration and optional Core ML on Apple silicon.

**Run status: Not run: commands checked against the official docs only.** Commands checked against the official docs on 2026-10-15. Not run end to end.

**This script:** The wrapper scripts are generated from the site data. Every .sh passed bash -n and shellcheck and ran in plan mode on Linux (Debian 13). Every .ps1 passed the PowerShell parser and chat.ps1 ran in plan, verify and rollback mode under PowerShell 7 on Linux with Windows calls mocked. Not run on macOS or real Windows.

## One command

```bash
curl -fsSL https://insidethemachine.ai/install/whisper-cpp.sh | bash
```

Actions: `| bash -s -- plan` (print only), `verify`, `rollback --yes`. Env: ITM_RAM. Read the script first: `curl -fsSL https://insidethemachine.ai/install/whisper-cpp.sh | less`.

Lines marked YOU RUN are not run by the script (servers, interactive apps, your own files). The script prints them at the end, in order.

## Steps

### macOS

Install:

1. **Install whisper.cpp**
   - run (macOS only): `xcode-select --install   # skip if already installed`
   - run (macOS only): `brew install cmake`
   - run: `git clone https://github.com/ggml-org/whisper.cpp.git && cd whisper.cpp`
   - run: `sh ./models/download-ggml-model.sh base.en`
   - run: `cmake -B build && cmake --build build -j --config Release`
2. **Configure (your choices)**
   - note: optional: Core ML encoder on the Apple Neural Engine; see the README's 'Core ML support' section

Verify:

- `./build/bin/whisper-cli -f samples/jfk.wav` → expect: prints a transcript of the bundled JFK sample

Rollback:

- run: `rm -rf whisper.cpp`

### Linux

Install:

1. **Install whisper.cpp**
   - run: `git clone https://github.com/ggml-org/whisper.cpp.git && cd whisper.cpp && sh ./models/download-ggml-model.sh base.en && cmake -B build && cmake --build build -j --config Release`
2. **Configure (your choices)**
   - note: optional: Core ML encoder on the Apple Neural Engine; see the README's 'Core ML support' section

Verify:

- `./build/bin/whisper-cli -f samples/jfk.wav` → expect: prints a transcript of the bundled JFK sample

Rollback:

- run: `rm -rf whisper.cpp`