How to use the API function

[Georgeye458]

Checks

• This template is only for usage issues encountered.
• I have thoroughly reviewed the project documentation but couldn't find information to solve my problem.
• I have searched for existing issues, including closed ones, and couldn't find a solution.
• I confirm that I am using English to submit this report in order to facilitate communication.

Environment Details

Python 3.10, GPU Docker deployment on Runpod.io

Steps to Reproduce

I really like this model and would like to do further testing with it. I can currently use it on Google Colab fine. Would we be able to provide documentation on how to use the API as I have now deployed it on to a more cost effective solution on Runpod.io

✔️ Expected Behavior

Documentation on API functionality. How it receives the audio file and response for the output audio files.

❌ Actual Behavior

No documentation. Thank you.

[SWivid]

could you elaborate on the difference of your usage between colab and runpod?
what kind of usage do you expect now, input/output/format/etc.?

[Georgeye458]

Thank you for your prompt reply.

I expect the input to be:

• Audio file (maybe it's a link)
• ref text
• gen text
  The output to be:
• Audio files generated by the model returned

I am expecting a POST GET interaction.
I realised today that a similar issue was discussed in #329
Any chance there is a solution to share?

[SWivid]

check for readme and also some issues related
https://github.com/SWivid/F5-TTS/tree/main/src/f5_tts/infer#socket-realtime-client