Description
OpenAIAudio component is a component that works with OpenAI's AI functionality.
To use the OpenAIAudio component, you need to obtain an API Key in advance in order to call OpenAI's AI functions. Please refer to OpenAI API Key Setup for how to obtain an API Key.
Component properties
| Property Name | Description | Example |
|---|---|---|
| Basic Properties | Specify the basic properties of the "OpenAI" category | |
| API Key | API Key ※1 | |
| Organization Id | Organization ID ※1 | |
| User | User Name | |
| Operation | Choose a process from Transcription Translation | Transcribe Translation |
| Model | Select the model name you want to use or enter it manually | Whisper-1 |
| Audio File | Sound filename | |
| Language | Language of speech Specify in ISO-639-1 format. Default is English. | ja en |
| Prompt | Prompt | |
| Temperature | Specify sampling temperature from 0 to 1. | |
| Response Format | Select output data format from JSON Detailed JSON Text SRT File VTT File | JSON Verbose JSON Text srt vtt |
* Refer to OpenAI API Reference for details of each OpenAI related property.
※1 To use OpenAIAudio components, you need to obtain an API key, see OpenAI API Key Setup for how to obtain an API key.
Output payload
| Output payload | Description |
|---|---|
cv.Payload | Response Format property Stores the contents specified in the output data format. |