whisper.cpp
C/C++ port of OpenAI's Whisper for fast offline speech-to-text on your own hardware.
These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.
1 more ways to get whisper.cpp
Package managers
- Chocolatey
choco install whisper-cpp
About whisper.cpp
whisper.cpp reimplements OpenAI's Whisper speech recognition model in plain C and C++ on the ggml library. It transcribes audio locally without Python, and runs on ordinary CPUs as well as GPUs.
It ships command-line tools for transcription and can also be embedded in other programs, which is why many desktop transcription apps build on it. It suits people who want private, fast transcription from the terminal.
Strengths
- Transcribes speech fully offline
- No Python dependency
- Runs on CPU or GPU
- Very active development
Limitations
- Mainly a command-line tool with no bundled graphical interface
- Models must be downloaded separately
Details
- Pricing
- FreeFree and open source.
- License
- MIT
- Developer
- ggml-org
- Platforms
- Windows, macOS, Linux, Command line
- How it runs
- Downloadable app
- Account
- Not required
- Works offline
- Yes
- Best suited for
- Private, fast speech-to-text from the command line
- Categories
- Audio tools, Local AI tools
- Last verified
- Added
- Provenance
- Facts checked against the developer's own pages and store listings, 1 sources on file.
Alternatives to whisper.cpp
Compare allSoftware that can replace whisper.cpp for an important use case, and what changes if you switch.
Whisper
An open-source speech recognition model from OpenAI for transcribing and translating audio on your own machine.
Whisper is the original OpenAI model in Python, adding translation to English and language identification, but larger models are slow without a capable GPU.
WhisperX
A speech recognition tool that adds word-level timestamps and speaker diarization to Whisper transcription.
WhisperX adds word-level timestamps and speaker diarization, but requires Python with CUDA and cuDNN, and its license is not stated.
Buzz
Turn speech recordings into text with a desktop transcription app.
Buzz provides a free MIT-licensed desktop interface for transcription on Windows, macOS and Linux, with microphone input and subtitle exports instead of command-line use.
Vibe
Transcribe audio and video files on your own computer.
Vibe is an MIT-licensed desktop app for transcribing audio and video files locally, with batch jobs and several transcript or subtitle formats.
MacWhisper
A Mac app that transcribes audio and video files to text on your own machine.
MacWhisper is a closed-source freemium macOS app with a graphical interface, several model choices and speaker recognition, instead of a cross-platform command-line tool.
noScribe
Transcribes recorded audio to text on your own computer, with speaker separation.
noScribe is a GPL-3.0 desktop app that transcribes recordings locally with speaker separation, though it is slow without a capable GPU.
aTrain
Transcribe recorded interviews on your own computer.
aTrain is an AGPL-3.0 app for local interview transcription with speaker detection, available on Windows and Linux but not macOS.
whisper.cpp as an alternative
Listings that name whisper.cpp as an alternative.
Meetily
Record and transcribe meetings with local AI processing.
whisper.cpp is a fast offline speech-to-text command-line tool with no Python dependency, requiring separate model downloads and offering no graphical meeting recorder.
Similar software
Related functionality, not necessarily a direct replacement.
Handy
Dictate into desktop text fields with local speech recognition.
Superwhisper
A voice dictation app that turns speech into text in any app, using offline or cloud recognition.
llama.cpp
The C++ engine most local AI apps are built on, running language models on ordinary hardware.
llamafile
Packages a language model and the code to run it into one executable file that works on several operating systems without installation.
