Description

The Whisper Interface Asset (IA) is an off-the-shelf component of Intuiface that enables you to submit a voice recording to the OpenAI Whisper Large Language Model (LLM) and then receive a transcript of that recording. This IA uses the OpenAI Audio Transcription API.

Adding the Whisper IA into your experience

The Whisper Interface Asset can be added to any experience using the "Add an interface asset" option located within Composer's Interface Assets panel. You will find two options in the OpenAI section:

The Player and Player Classic versions work identically. The only difference is under the covers and thus irrelevant to the interface asset's use.

Configuring the Whisper IA

To use the Whisper Interface Asset, you must assign it an OpenAI API key. An API key is acquired by creating an OpenAI account and then purchasing tokens. (Each GPT prompt and response consumes tokens, and those tokens have a cost.)

Once you have an account and have purchased tokens, head to the OpenAI API Key page to find your key.

This key should be pasted into the "OpenAI API key" property for the Whisper Interface Asset:

Creating and sending a recording

To create and send a recording, you need to call the "Start recording" and "Stop recording and transcribe" actions.

• Start recording
  The Intuiface experience will start to record audio captured through the device's default microphone.
• Stop recording and transcribe
  The recording is stopped and then sent to the OpenAI Audio Transcription API.

Accessing the transcription

The transcription is accessed via the read-only parameter "Transcribed text" associated with the trigger "Transcription received".

As with all trigger-associated read-only parameters, the value of 'Transcribed text' is accessed via binding in the Action pane of the Triggers and Actions panel.

Additional triggers 

Triggers

• Error message received
  Raised when an error is returned instead of a response.
  
  • read-only parameter: Error message
    This parameter contains the error message.