How to use Whisper CPP: what you can do with it

3 use cases

• Transcribe audio files offline on your own machine

  Build whisper-cli, download a ggml model and turn recordings into text without any cloud service.

  • REPO ggml-org/whisper.cpp
  • Claude Code
  • Codex
  • Cursor
  • Content
  • Beginner
  View prompt

  Clone ggml-org/whisper.cpp, build whisper-cli with CMake, download the base.en model, convert every MP3 in <folder> to 16 kHz mono WAV with ffmpeg and transcribe each one. Save one text file per recording next to the audio.

  Share Email me this

• Run bigger Whisper models on small hardware with quantization

  Quantize a ggml Whisper model to Q5_0 so it uses less memory and disk with the same commands.

  • REPO ggml-org/whisper.cpp
  • Claude Code
  • Codex
  • Cursor
  • Content
  • Intermediate
  View prompt

  Using ggml-org/whisper.cpp, quantize the <model> ggml model to q5_0 with the quantize tool, then transcribe <test files> with both the original and the quantized model. Report memory use, run time and any differences in the transcripts.

  Share Email me this

• Speed up transcription on a Mac with the Neural Engine

  Generate a Core ML encoder so Whisper CPP runs the encoder on the Apple Neural Engine, more than 3x faster than CPU only.

  • REPO ggml-org/whisper.cpp
  • Claude Code
  • Codex
  • Cursor
  • Content
  • Intermediate
  View prompt

  On my Apple Silicon Mac, set up ggml-org/whisper.cpp with Core ML support: install the Python requirements, generate the Core ML encoder for base.en, rebuild with WHISPER_COREML=1 and transcribe samples/jfk.wav. Tell me how long it took compared with the CPU build.

  Share Email me this

Quick start with Whisper CPP

1. Check you have what it needs: A C/C++ toolchain and CMake to build from source; ffmpeg to convert audio to 16-bit WAV, since whisper-cli reads 16-bit WAV files; Disk and RAM for the model you pick: about 142 MiB and 388 MB for base, up to 2.9 GiB and 3.9 GB for large.
2. Open ggml-org/whisper.cpp on GitHub and read the README and license.
3. Run git clone https://github.com/ggml-org/whisper.cpp.git and cd into the folder
4. Download a model with sh ./models/download-ggml-model.sh base.en
5. Build the tool: run cmake -B build and then cmake --build build -j --config Release
6. Convert your recording to 16-bit WAV with ffmpeg -i input.mp3 -ar 16000 -ac 1 -c:a pcm_s16le output.wav

These steps come from our top use case, Transcribe audio files offline on your own machine, which also has a copy-paste agent prompt.

Using the Deduped MCP, get the setup steps for ggml-org/whisper.cpp

claude mcp add --transport http deduped https://dedupedai.com/mcp

Best AI repos for Content

About this repo

• Who it is forDevelopers, podcasters and privacy-minded users who want fast local transcription without sending audio to a cloud API.
• Why it is hot55k stars, talked about in 2 AI sources we track
• LanguageC++
• Sourcegithub.com/ggml-org/whisper.cpp · Back to Hot repos

Requirements

• A C/C++ toolchain and CMake to build from source
• ffmpeg to convert audio to 16-bit WAV, since whisper-cli reads 16-bit WAV files
• Disk and RAM for the model you pick: about 142 MiB and 388 MB for base, up to 2.9 GiB and 3.9 GB for large
• Optional: Xcode command line tools and Python 3.11 for Core ML on Apple Silicon

Related repos

• Trended earlier REPO nyosegawa/speech.cpp Speech CPP speech.cpp is a C++ command and library on ggml for speech synthesis, speech recognition and voice activity detection, running on the CPU, Metal or Vulkan with an OpenAI-compatible server.
• Trended earlier REPO SYSTRAN/faster-whisper Faster Whisper faster-whisper is a Python reimplementation of OpenAI's Whisper built on the CTranslate2 inference engine. It is up to 4 times faster than openai/whisper at the same accuracy while using less memory, supports 8-bit quantization on CPU and GPU, batched transcription, word-level timestamps, Distil-Whisper checkpoints and a built-in Silero VAD filter.
• Trended earlier REPO OpenWhispr/openwhispr Openwhispr OpenWhispr is a free, open-source alternative to WisprFlow and Granola. Press a hotkey, speak and your words appear at your cursor, using fully offline speech-to-text models such as Whisper and NVIDIA Parakeet or cloud providers. It also transcribes meetings with speaker diarization, keeps searchable notes, offers a Voice Assistant hotkey that sends commands to GPT, Claude, Gemini or local models, and has a public API and MCP server.