Hi!
I’ve started my deepdive into OpenAI and Power Platform and made some good solutions for integrering with both text- and chat completion, through a custom connector with different suitable actions. Works GREAT!
I’ve glanced at their Whisper-model, and want to make use of speech-to-text-functionality in Power Platform. Just for fun, at least now to begin with.
Where I struggle; the content-type for the api-call is multipart/form-data, so I find i a bit challenging getting the body correct. Works great in Postman, but in Power Automate it’s a no-no.
Anyone looked into it and able to point me in the right direction?
Here’s the curl in raw format:
curl https://api.openai.com/v1/audio/transcriptions \
-X POST \
-H 'Authorization: Bearer TOKEN' \
-H 'Content-Type: multipart/form-data' \
-F file=@/path/to/file/audio.mp3 \
-F model=whisper-1