I've looked at the codebase. The ones I listed do a significant amount of audio processing to get better transcripts, avoid the "Thank you" issues with whisper large turbo, handle bluetooth and noisy environments.
Hopefully VoiceInk gets there. It is a neat project and really well done for a first time dev but rough around the edges. Careless is ~20$ and if you just need dictation is the best option.
Hopefully VoiceInk gets there. It is a neat project and really well done for a first time dev but rough around the edges. Careless is ~20$ and if you just need dictation is the best option.