Audio to text command
Converts audio to text by applying powerful neural network models. It accepts an audio file that may be recorded from a device and creates a text file that contains the textual translation of the audio file.
Parameters
| Name | Type | Possible values | Description |
|---|---|---|---|
|
Device audio URL |
String |
The URL to the audio file of the device (as, for example, returned by the Start audio recording command). |
|
|
Audio file key |
Media |
The full repository path, including directory and file name, where to locate the audio file. You can select a file that already resides in the Perfecto repository or select a file from your computer that is then uploaded to the Perfecto repository. To learn more about the Perfecto repository, see Manage the repository. Click the Select media link, browse to the file, and then click SELECT. Example: |
|
|
Result variable |
String |
The variable to receive the retrieved values. |
|
|
Language |
String |
US English | UK English | Spanish | Japanese | French | Chinese | Portuguese | Arabic |
The supported audio file languages. |
|
Rate |
String |
Broad | Narrow |
The sampling rate of the audio recording |
|
Profile |
String |
Performance | Accuracy |
The profile of the NLP network |
|
Phrase |
String |
A list of phrases for the speech-to-text library to use to avoid confusion. For example, provide the words ‘two’ and ‘four’ to avoid confusion with ‘to’ and ‘for’. In the Value column, click Edit to add a phrase. A phrase can be based on as a constant, a variable, or a DataTable. |
|
|
Dictionary |
String |
A dictionary for the speech-to-text library to use. In the Value column, click Edit to add a dictionary entry. A dictionary entry can be based on as a constant, a variable, or a DataTable. |
|
|
Comment |
String |
Adds a comment to the script. |
|
|
On-fail Result* |
Condition |
Ignore | Break | Continue | Abort | Catch |
The behavior when the command fails. |
* Mandatory parameter