Can I get speaker diarization using openai api on node.js?

API
,
1

Greetings.
I want to get speaker diarizatino of my call recording audio file on node.js project.
But I cannot find an API to get speaker diarizations. I already used transcribe API to get transcription so I just want to keep my eyes on oepnai to get speaker diarization.
Could you help me?
Let me share my code which getting transcription on my node.js project.

const transcription = await openai.audio.transcriptions.create({
      model: "whisper-1",
      file: fs.createReadStream(fullFilePath),
    })
1 Like
2

This is not a feature of the current Whisper 2 API, it may be included with Whisper 3 (soon to be launched, no dates yet) but that is unknown.

1 Like
3

There are several solutions available already. You can look in the Whisper Github repo or look for separate repos like this one.

1 Like
4

Thanks. But as I said, I want to get that info on my node.js project.
So I think there should be an API or SDK to get speaker diarization.
Am I right?

1 Like
5

Then, how can I get speaker diarization info on my node.js platform?
Please let me know.

1 Like
6

@healer, Did you have any success finding a Node.js solution?