Why are you planning to store voice, if you don't store text? (Maybe you meant - "text messages are not stored within your file manager"?)
You're building an app for communication, you say. So the first priority is to keep the conversation thread intact. A user should be able to review all communications in a conversation, including voice (of course) and text. This has to be availabe in the conversation, not (only) in the file manager.
Depending on the additional use cases, you might want to store re-usable communications (such as images) in a "file manager" to help find them quickly for sharing again. But I'm wondering whether you app should include its own file manager (and storage space, I assume), since oftentimes, people also want to share stuff from outside your app: Images from the camera, audio from a dictation, maybe even documents uploaded to the mobile from a laptop. So instead of creating your own file manager and limiting people to re-use only files managed by your app, I'd recommend to integrate into the platform and access the standard (or user-installed) file manager and default storage spaces.