Amazon Polly is only configured to do one voice at a time. The developers decided not to support the SSML <voice> tag which would have made it easy to change voices for one encoding. Microsoft and Google support this so perhaps one day Amazon Polly will, too?
For now, you can manually combine two .mp3 files together relatively easily through a Command line. If you do a Bing/Google search you'll find the commands to do this.
Converting long text to audio with Polly using S3 systhesis - failureAccepted Answerasked a month ago
Polly: GetSpeechSynthesisTask return length of audioasked a month ago
joining email talk to text with AWSasked a month ago
Polly for Windows Plugin Fails on Some Voicesasked 2 months ago
why does the whisper action on the polly console only work for the Mathew voice?asked 3 months ago
CloudWatch Dashboard: Is there a way to create a link to a specific Text widget?asked 3 months ago
Is there a way to grab a user's voice utterance from an Amazon Lex V2 bot using Lambda calls?asked 5 months ago
AWS MediaConvert - Generate a waveform image from an audioasked 2 months ago
Simulate conversation with using two different voices?asked 9 months ago
Are 'direct' derivative works of the recordings allowed?asked 2 years ago