For a task in my application I have to get a response from chat gpt, then for the voice sending a request to tts endpoint with the response provided by chat gpt and then to get the duration of specific words in the audio I will be sending the audio to whisper API.
Since in the TTS request, audio and text both are available, I believe there should be a way to include the whisper API abilities in the same request instead of sending 3 different requests each time.
Please let me know if this is already available or I am doing something wrong