I am making a language app and I want to be able to pronounce specific words in a given language. For example, I want a sound file pronouncing “espirales” (Spanish)
If I input this into the TTS api using Shimmer, I just get some nonsense. There are some words that would be considered English words too (e.g. embargo) that would have a different Spanish pronunciation. When I put in a full Spanish sentence, or single English Words, it pronounces it very well.
Can TTS be prompted or a language set?