---
title: "Comment by Nick Ra on \"Integrate Open AI Whisper API in Android\" | Hashnode"
description: "Thank you for this very helpful tutorial! Any idea how user's input from microphone could be sent for inference?"
url: "https://hashnode.com/posts/integrate-open-ai-whisper-api-in-android/66f54a00759bfb236da693cf/comment/67f84681466d81e79e2a8fec"
---

[Discussion](https://hashnode.com/posts/integrate-open-ai-whisper-api-in-android/66f54a00759bfb236da693cf)

Comment [Integrate Open AI Whisper API in Android](https://hashnode.com/posts/integrate-open-ai-whisper-api-in-android/66f54a00759bfb236da693cf)

[Nick Ra](https://hashnode.com/@rabyunghwa)

[Apr 10, 2025](https://hashnode.com/posts/integrate-open-ai-whisper-api-in-android/66f54a00759bfb236da693cf/comment/67f84681466d81e79e2a8fec)

Thank you for this very helpful tutorial! Any idea how user's input from microphone could be sent for inference?

[Asim Latif](https://hashnode.com/@asimxlatif)

[Apr 11, 2025](https://hashnode.com/posts/integrate-open-ai-whisper-api-in-android/66f54a00759bfb236da693cf/comment/67f84681466d81e79e2a8fec#reply-67f8978dd60589ef9935e01e)

Hello Nick, the api code is same for all audio files. But you need to amke sure that you are building recorded file in correct way and its uri is available for operations.

In case you need code, you can reach out to me via dm or on linkedin.
