Transcribe audio with OpenAI

You can transcribe audio via OpenAI and use the result in your bot conversation.

Step 1. Add and set up the OpenAI integration.

Navigate to the organization integrations section:

Add the OpenAI integration:

Step 2. Add bot variable of type Audio Transcription:

Select the previously configured integration. Adjust the parameters according to the documentation. Bot variable syntax is allowed in the parameters so that they can be dynamic. One required parameter is the uploaded file. Note that we are using another bot variable here and using the special syntax {{audio_transcription_file.value}}. In our example, the audio_transcription_file bot variable is a step variable of type File upload:

It is also recommended to limit the types of uploaded files to audio via the file upload step settings:

The result of such a bot variable is the audio transcription text of the audio file that can be used in the bot conversation, for example, in the text chat text type:

Note that if the file upload step allows more than 1 file to be uploaded, the result transcription will contain the transcription of all uploaded files.

Edit this page

See also