I’m evaluating Remio and I would like to clarify a few points about its transcription features before purchasing.
- Can I upload existing audio files, such as MP3 recordings, and have Remio transcribe them automatically?
- Are there any limits on the duration or size of uploaded audio files for transcription?
- Which transcription engine does Remio use? For example, is it based on Whisper, Whisper.cpp, another open-source model, or a proprietary/local model?
- Is the transcription performed fully locally on the user’s device, or are audio files ever uploaded to Remio or third-party servers?
- Finally, does Remio support transcription in Italian, and how reliable is it for long recordings such as lectures or interviews?

Thank you very much for your help.