How to access audio format of user response given to Alexa for Further use

Question

After user give respond to Alexa we capture that in slots, then how can we access that responses in audio format directly in Alexa skill?

For example : User -> run survey skill , Alexa -> Sure , first tell me how are you? , User -> Well, I am doing good.

In this example i want to access audio format of user response " Well, I am doing good." in raw audio format without speech-to-text processing with original tone and sarcasm of user for further use.

user_response = context.request.intent.slots["user_response"].value

# Generate a TTS audio response.
tts_audio_response = ask_sdk_core.speech.synthesize(user_response)

# Return the TTS audio response to Alexa.
response = context.response

I tried this code but how can i access it not getting?

Answer 1

I don't believe your skill can access the user's raw audio input or any of its emotion / tone / metadata. Skill input is limited to the intent that the input matched and a text representation of any slot values they provided.