If you have a homelab or vps you could try rolling your own with https://hub.docker.com/r/onerahmet/openai-whisper-asr-webservice for the transcription and a foss Tasker alternative for retreiving the voicemail when your dialler app posts a voicemail notification. If you don’t have the capability to selfhost whisper, you’d probably have to sacrifice the illusion of privacy (your mobile carrier will always have access to any calls made over their network) and use a transcription service from google/microsoft/openai.
Asterisk https://www.asterisk.org/ might be worth a look too (i.e. selfhost your voicemails)
Something like this should work on linux or mac. On windows you’ll probably need to use wsl or convert it to powershell if you can’t install the dependencies natively. The script requires bash, unrar, and find.
#!/usr/bin/env bash while read -r rarfile; do while read -r password; do if unrar t -p"$password" "$rarfile" >/dev/null 2>&1; then echo "$rarfile $password" break fi echo "$rarfile password not found" done < /path/to/passwords.list done < <(find /path/to/rars -type f -iname '*.rar')