whisper.cpp
C/C++ port of OpenAI's Whisper speech recognition that transcribes audio offline on your own computer or phone.
AI Audio & VoiceFreeverified Listed on Open source
Is whisper.cpp free?
Yes, whisper.cpp has a free plan. What you get: Open source (MIT): free C/C++ speech recognition you build and run yourself. To get it: clone the repository from GitHub; then download a ggml Whisper model with the included script; then build it and run whisper-cli on an audio file. Verified on github.com.
Free plan at a glance
- Includes
- Open source (MIT): free C/C++ speech recognition you build and run yourself
MIT-licensed code that runs on your own device; the repository states no usage limit.
- Duration
- Free forever
- Commercial use
- Allowed on the free plan
How to get it free
Self-host- Clone the repository from GitHub
- Download a ggml Whisper model with the included script
- Build it and run whisper-cli on an audio file
Good to know
- Inference only
- You build and run it yourself
github.com, Checked Source
Overview
whisper.cpp is open-source code that runs OpenAI's Whisper speech-to-text model on your own device, with no dependencies and no internet connection needed. You build it yourself and download the model you want.
Key features
- Plain C/C++ implementation without dependencies
- Runs fully offline on-device, including on iPhone
- Optimized for Apple Silicon, and supports NVIDIA, AMD and Vulkan GPUs or CPU only
- Integer quantization to cut memory and disk use
- Real-time microphone transcription example
- Voice Activity Detection support
Best for
- People
- Developers adding offline transcription to apps, Privacy-minded users who keep audio on their own machine, Hobbyists running speech recognition on a Mac, Raspberry Pi or phone
Limitations
- Inference only: it does not train models
- You build it from source and download models yourself
- The real-time microphone example is described as naive
Screenshot
FAQ
- Is whisper.cpp free?
- Yes. whisper.cpp has a free plan: Open source (MIT): free C/C++ speech recognition you build and run yourself. We last checked github.com's pricing page on 2026-11-12.
- What does the whisper.cpp free plan include?
- Open source (MIT): free C/C++ speech recognition you build and run yourself. Source: https://github.com/ggml-org/whisper.cpp (checked 2026-11-12).
- How do I get whisper.cpp for free?
- Steps: Clone the repository from GitHub; Download a ggml Whisper model with the included script; Build it and run whisper-cli on an audio file. Start at https://github.com/ggml-org/whisper.cpp (checked 2026-10-28).
- Do I need an account to use whisper.cpp for free?
- Not for the free option: the free route is to self-host whisper.cpp (Clone the repository from GitHub). Checked 2026-10-28.
- What's the catch with whisper.cpp's free plan?
- Inference only. You build and run it yourself. Checked 2026-10-28.
- What are free alternatives to whisper.cpp?
- TurboScribe, Notta and Typeless all have free plans. We checked their free offers on 2026-11-12.
- Does whisper.cpp work offline?
- Yes. The README shows it running fully offline and on-device on an iPhone 13.Source: github.com/ggml-org/whisper.cpp
- Which platforms does it support?
- Mac OS (Intel and Arm), iOS, Android, Java, Linux / FreeBSD, WebAssembly, Windows, Raspberry Pi and Docker.Source: github.com/ggml-org/whisper.cpp
Free alternatives

TurboScribe
Unlimited AI transcription powered by Whisper.
Free forever, 3 files per day up to 30 minutes each

Notta
AI transcription and meeting notes.
Free forever, Monthly transcription minutes

Typeless
AI voice keyboard that turns speech into cleaned-up text in any app, on Mac, Windows, Linux, iOS and Android.
Free forever, Limited words each week, standard accuracy

OpenWhispr
Open-source dictation app that types your speech into any app, with local or cloud models and meeting notes.
Free forever, Unlimited local dictation, 2,000 cloud words per week

Rev
AI transcription and investigation platform: transcribes recordings and lets you search and cite them across case files.
Free forever, 45 AI transcription minutes per month, English only, 1 user
More free AI Audio & Voice tools
- Spleeter

Free forever, Open source (MIT): free Python library that splits music into 2, 4 or 5 stems
- Speechnotes

Free forever, Unlimited dictation in the online notepad and Chrome extension, with ads
- Amical

Free forever, Unlimited local dictation, 2,000 cloud words per week
- MLX-Audio
Free forever, Open source (MIT license): free audio AI library you run on Apple Silicon Macs
- FreeFlow

Free forever, Open source (MIT): free Mac dictation app; bring a free Groq API key
- Abogen

Free forever, Open source (MIT license): free desktop and web app that runs offline on your computer
Sources
- Free offer
- Verified on github.com/ggml-org/whisper.cpp/blob/master/LICENSE
…is hereby granted, free of charge, to any person obtaining a copy of this…
- Page content
Checked against
Added by our team. We check that a free option exists and record the date; signing up is between you and whisper.cpp, so read their privacy policy and terms first.
Is this your tool? Claim it · Promote it