Speaker identification

[burnt heart]

Thanks for asking your question. Please be sure to reply with as much detail as possible so we can assist you efficiently. Such as:

• Provide the request_id if you've a question about a transcription response.
• The options you used or the api.deepgram.com URL you sent your request to, including parameters.
• Any code snippets you can include.
• Any audio you can include, or if you can't share it here please email it to us at [email protected] and provide a link to this thread.

[rancid dagger]

Hi @tidal mortar,

Deepgram has the diarization feature. While we don't identify speakers for you, there are ways to implement some logic to do this yourself, although it's a hack for sure, and it only works for certain use cases

One of our users, Wes Bos, uses Deepgram to transcribe his podcasts. He has the hosts say a specific phrase unique to each speaker at the end of the podcast, which allows him to identify who speaker 0 is, speaker 1 is etc. He explains how he does it in this podcast at 21:31 (Topic 21 ) https://syntax.fm/show/686/we-need-your-help-with-the-secret-sauce/transcript. I believe the github project with the code is here: https://github.com/wesbos/Syntax-AI-Transcripts/tree/main Check out the deepgram folder in that project.

But unfortunately, Deepgram doesn't have a speaker recognition feature at the moment, just the diarazation feature. But some users have asked for it. I will relay to the product team that this is a request from you.

[tidal mortar]

Thank you Sandra