A system may include servers. The servers may include memories including a first database to store voicemail message information associated with a voicemail mailbox and a user device, and a second database to associate a plurality of user devices with a voice-to-text transcription service; and a receiver to receive a new voicemail message associated with the voicemail mailbox. The servers may also include a processor to query to the second database to determine whether to request a voice-to-text transcription of an audio file associated with the new voicemail message and to determine whether to notify the user device of the new voicemail message before or after receiving the voice-to-text transcription of the audio file. The servers may also include a transmitter to send a notification of the new voicemail message to the user device according to the determination of whether to notify the user device of the new voicemail message before or after receiving the voice-to-text transcription of the audio file.