Whisper

Generate ASMR-inducing audio, providing immersive auditory experiences in your flows.

Description

The OpenAI component allows you to integrate OpenAI Whisper generation into your flows. In particular, the following versions are supported:

• Whisper-1

Whisper is an AI model developed by OpenAI. Whisper is a powerful tool for converting spoken language into text, with capabilities that extend to multiple languages and various audio conditions.

The OpenAI component has the identifier of opa-X, where X represents the instance number of the OpenAI component.

Inputs

The OpenAI component has the following input connections.

Input Name	Description	Constraints
From Data Loaders	This input connection represents the context information for the OpenAI model.	Must originate from a Data Loader, Data Source or VectorDB component.
From Audio Input	This input connection represents the user query for the OpenAI model.

Component settings

Parameter Name	Description
Credentials	You can specify to use your own OpenAI credentials or alternatively you can use Diaflow's default credentials.
Model	This parameter specifies the version of OpenAI that the component should use. Available values: - Whisper-1
Endpoint	Available options: - Transcriptions - Translations
Data source

Advanced configurations

Options	Description
Temperature	This parameter is used to control the level of randomness or creativity in the generated ASMR content. A lower temperature value results in more deterministic and conservative outputs, while a higher temperature value encourages more diverse and creative variations in the generated audio. Adjusting the temperature parameter allows users to fine-tune the balance between predictability and novelty in the Whisper-generated ASMR content, catering to individual preferences for relaxation and sensory pleasure.
Response format	Specified the format of the output audio data.
language	For more accurate results, specify the input language from this dropdown box.
Prompt	Describes how you want the OpenAI model to respond. For example, you can specify the role, manner and rules that OpenAI should adhere to. Also mention the component ID to connect the components.

Outputs

The OpenAI component has the following output connections.

Output Name	Description	Constraints
To Output	This output connection contains the audio data result of the OpenAI component	Can be connected to any component that accepts a string input or audio input.

Use case

Here is a simple use case of the Whisper component, where the Whisper component is being used with the whisper-1 model to translate an audio into a text.