OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Audio & Voice AI

Whisper.cpp

Whisper.cpp is a C/C++ implementation of OpenAI’s Whisper automatic speech recognition model. It provides inference for speech-to-text, a command-line transcription example, and a C-style API for application integration.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Whisper.cpp — OpenViST project profile in Audio & Voice AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Whisper.cpp when you need to run Whisper speech-to-text inference in a C/C++ project or want a repository-provided CLI workflow for transcribing WAV audio.

Who it is for

  • C and C++ developers adding speech recognition or transcription to applications
  • Developers building local audio-processing workflows
  • Users who want to run the documented command-line example on WAV files

Documented uses

  • Transcribe a supported audio file with the whisper-cli example
  • Use Whisper inference as a component in a C/C++ application
  • Choose among model sizes and quantized models based on available disk and memory
Before you choose

Requirements & limits

The repository is public and identifies the project as MIT-licensed.

  • The CLI currently accepts 16-bit WAV files; other audio may need conversion.
  • Model size affects disk and memory use: the README lists approximate memory from 273 MB for tiny to 3.9 GB for large.
  • Quantization can reduce model disk and memory requirements, with processing efficiency depending on hardware.
  • The README lists multiple platforms and acceleration options; the appropriate path depends on the target system.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Build the CLI and transcribe a WAV sample

Compile the whisper-cli example and use it to transcribe a 16-bit WAV file.

Before you start

  • A cloned whisper.cpp repository
  • CMake and a C++ build environment
  • A Whisper model converted to ggml format
  • A 16-bit WAV audio file

Steps

  1. Clone the repository and change into its directory.

  2. Download a model, for example with the command below.

    Documented command
    sh ./models/download-ggml-model.sh base.en

  3. Build the example with cmake -B build and cmake --build build -j --config Release.

  4. Run ./build/bin/whisper-cli -f samples/jfk.wav, or provide the path to a 16-bit WAV file.

Expected outcome

The CLI runs Whisper inference on the selected WAV input.

Guide limitations

  • The documented CLI currently runs only with 16-bit WAV files; the README shows ffmpeg conversion for other audio formats.
  • Model choices have different disk and memory requirements.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Model inference and serving

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Whisper.cppTranscribe a supported audio file with the whisper-cli exampleThe repository is public and identifies the project as MIT-licensed.
BluettsGenerate speech audio from text in a supported language.CLI, Linux, macOS, WindowsThe repository is public and identifies the project license as MIT.
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
ggml-org/whisper.cpp · Official homepage title · retained in its source language
How we review sourcesSuggest a correction