I have a use case like the following - we have a language learning app and users can tap on any word

I have a use case like the following - we have a language learning app and users can tap on any word and listen to how its pronounced. We are using Google Text to Speech API for this. To save costs, we want to cache the response from the API. These are mostly short audio of one or two words. Would KV be a good fit for this compared to CF Cache API?
Was this page helpful?