whisper.cpp
By ggml.ai (part of Hugging Face) / open source · github.com/ggml-org/whisper.cpp
3,4 Good
Transcribe speech to text entirely locally with OpenAI's Whisper models. Sensitive meetings and interviews never leave the computer.
Best for: Transcription of sensitive material that must never leave the computer.
Pros
- Transcribes Swedish surprisingly well completely offline
- Free and open source under MIT license
- No subscriptions or per-minute fees at all
Cons
- Command line: easier packages exist but require some searching
- Slower than cloud services on weak hardware
- No speaker diarization without add-ons
Quick facts
| Price | Free |
|---|---|
| Origin | Outside EU (ggml.ai (part of Hugging Face) / open source) |
| Categories | Local AI |
| EU data storage | No |
| GDPR terms (DPA) | No |
Sources & evidence
Claims about data storage, jurisdiction and compliance should be verifiable. Here is the evidence behind the statements above:
- whisper.cpp – GitHub repo (open source under MIT license, local C/C++ implementation of Whisper) →
- ggml.ai – Project page (the organization behind the ggml library; founded in 2023 by Georgi Gerganov, acquired by Hugging Face in 2026) →