- pricing
Standard audio time ~ 23h 8m (one million words) per 4.00 USD // ap-northeast-2 // Korean, Seoyeon, Female
- performance
almost real time
- input type
Text, SSML
- output type
Amazon S3
MP3, OGG, PCM, Speech Marks
- alternative
Naver CLOVA Voice - https://clova.ai/voice/
Google TTS AI - https://cloud.google.com/text-to-speech?hl=ko
- note
If you are going to integrate with AWS services, you must use it. It is absolute in terms of network cost and architecture.
- reference