For my project, I needed to convert text to speech and generate timestamps for each word. I spent days upon days trying to configure and work around several APIs and overengineered documentation until I found Unreal Speech. Within the same day, I had the API fully configured and turned four required APIs into two. The documentation was incredibly easy to understand and had code examples for each call in all common languages. The feature of Unreal Speech's API that left my jaw dropped was their automatic timestamping. Within the same call, I could get the audio file and the timestamps for every word, saving me an abundance of processing time, and boosting my program's efficiency. I use this API daily for all my TTS calls now, and with such ease of use and cheap pricing, I don't see myself ever changing that. Review collected by and hosted on G2.com.
The only real issue I've had with Unreal's API is the delays between punctuation. As far as I know from the docs, there's no way to do this, but if there was a way to be able to change that time, it would be perfect. Review collected by and hosted on G2.com.
