Perform speech to text using OpenAI
Provided an audio file, transcribe or translate the contents into text. This Wrk Action only supports files up to 25MB.
Application
Inputs (what you have)
| Name | Description | Data Type | Required? | Example |
|---|
| File | An audio file that will be converted into text. Supported file types are: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm | File | Yes | audio.mp3 |
| Conversion type | Transcription will record the speech in the same language it was spoken. Translation will record provided speech as English | Pre-defined choice list | Yes | Transcription |
| Prompt | You can use a prompt to improve the quality of the transcripts generated by the Whisper API. The model will try to match the style of the prompt, so it will be more likely to use capitalization and punctuation if the prompt does too. | Text (Long) | No | Ensure correct grammar is used |
| Language | If transcription is selected, the language of the input audio | Pre-defined choice list | No | English |
| Output filename | Optional custom filename for the generated audio file | Text(Long) | No | sample.mp3 |
Note: the value of inputs can either be a set value in the configuration of the Wrk Action within the Wrkflow, or a variable from the Data library section. These variables in the Data library section are the outputs of previous Wrk Actions in the Wrkflow.
Outputs (what you get)
| Name | Description | Data Type | Required? | Example |
|---|
| Recorded text | The transcribed or translated text | Text(Long) | Yes | |
Outcomes
| Name | Description |
|---|
| Success | This status is selected if the speech is recorded successfully to text |
| Impossible to complete | This status is selected in the event of the following scenarios:External system is not availableProvided file is not in the correct typeThe provided file is too large |
Requirements