Step 1. Set up OpenAI API Keys:** Go to [OpenAI API Keys](
https://platform.openai.com/account/api-keys) and create your API keys. You'll need to include these keys in your requests as "Bearer sk-*******************" in the authorization (Shared headers).
Upload Audio: Select your audio file within the supported formats.The audio file must be included in the file field of the action
Whisper is the model available right now. Use this model name for now. The file and the model name are the only required parameters for both the actions in the plugin
Get Transcript: Use the 'Whisper speech to text' action to receive the text transcript by uploading an audio file.
Translate: Use the 'Whisper translate' action from the plugins action to get the transcript in English.
This endpoint detect the language of the audio and translates it to English.
Allowed languages list :
https://github.com/openai/whisper#available-models-and-languages Important Tips:
File Size: Be mindful of the 25MB limit to avoid upload errors.
Format Support: Ensure your audio file is in one of the supported formats for seamless processing.
Find detailed documentation here :
https://platform.openai.com/docs/api-reference/audio
Built on Bubble
