I'm currently using the Speaches server along with Systran/faster-whisper-base for speech recognition into Emacs. I've modified natrys/whisper.el so that I can continuously queue transcription, have the outputs inserted at various points, and save the audio.

Related posts:

• Using whisper.el to convert speech to text and save it to the currently clocked task in Org Mode or elsewhere
• Emacs and whisper.el: Trying out different speech-to-text backends and models
• Queuing multiple transcriptions with whisper.el speech recognition
• Using Silero voice activity detection to automatically queue multiple transcriptions with natrys/whisper.el