XenoGuard 4.0 Documentation

Transcribe Audio

ActionStep Reference » OpenAI » Audio » Transcribe Audio

The OpenAI Audio Transcribing ActionStep is a workflow component designed to leverage the capabilities of OpenAI's transcription service. It facilitates the conversion of audio content into text format. This step can be integrated into various applications and systems to automate the transcription process.

[-] Hide
  1. Open the OpenAI node in the Workspace Explorer.
  2. In the Audio node, select the Transcribe Audio ActionStep.

Parameters:

The ActionStep has the following input parameters:


Name Description
API Key
The OpenAI API key.

Allowed Context Scopes
 [Fixed, Local, Global, Reference]
Allowed Context Types [Fixed, Variable, Parameter, Result, Enum]
Allowed Context Values [String]
Thread Name
A user-defined identifier that helps organize and manage chat interactions within the application or system. It allows users to associate the transcription request with a specific conversation or context.

Allowed Context Scopes
 [Fixed, Local, Global, Reference]
Allowed Context Types [Fixed, Variable, Parameter, Result, Enum]
Allowed Context Values [String]
Audio File
The parameter specifies the target audio file that needs to be transcribed. Users provide the audio content in a supported format to be processed by OpenAI's transcription service.

Allowed Context Scopes
 [Fixed, Local, Global, Reference]
Allowed Context Types [Fixed, Variable, Parameter, Result, Enum]
Allowed Context Values [String]
Timeout
The timeout in milliseconds for the API request.

Allowed Context Scopes
 [Fixed, Local, Global, Reference]
Allowed Context Types [Fixed, Variable, Parameter, Result, Enum]
Allowed Context Values [Int64]

Results:

The ActionStep returns the following results:

name Description
Success
Indicates the result of the OpenAI request.

Allowed Context Scopes
 [Fixed, Local, Global, Reference]
Allowed Context Types [Fixed, Variable, Parameter, Result, Enum]
Allowed Context Values [Boolean]
Output
The result text from the audio file.

Allowed Context Scopes
 [Fixed, Local, Global, Reference]
Allowed Context Types [Fixed, Variable, Parameter, Result, Enum]
Allowed Context Values [String]

Example 1 (Transcription Execution):

This example illustrates an ActionScript that initiates an audio transcription process using OpenAI's services. The script begins by setting parameters for execution mode and file paths, then runs a specific OpenAI transcription action. It uses an API key to authenticate and transcribes the audio from the provided file path, with a set timeout for the operation. Upon completion, the script successfully transcribes the audio content, as evidenced by the output in the results list, which includes a transcription stating that "OpenAI is a California-based company that focuses on the development and application of artificial intelligence."

 

See other operations:

Translate Audio To English
Text To Speech