I'm trying to add a transcript with multiple speakers to a voice comment through the API, following this documentation.
However, it's currently very limited as it does not allow for line breaks. This is an issue when you have two speakers as ideally you'd want it to render the transcription like this:
Speaker 1: Hello
Speaker 2: Hi
Speaker 1: How may I help you today?
Currently, the voice comment renders it all in a single (and difficult to read) line:
Speaker 1: Hello Speaker 2: Hi Speaker 1: How may I help you today?
As you can see, the latter is really tricky to read with lack of speaker separation. Would it at all be possible to make this change to at least enable line breaks in the transcription field?
Please sign in to leave a comment.