Is there a way of saving an audio clip of the user's first few utterances on a call? This would be useful for voice biometrics, where a file needs to be sent to the API to verify it. Hope that makes sense.
Vapi helps developers build, test, and deploy voice agents at scale. We enable everything in between the raw models and production, including telephony, test suites, and real-time analytics.
I can provide a workaround, but it requires substantial coding knowledge. Whenever a call is triggered and you're subscribed to the webhook request, you receive a http://vapi.daily.co/ link. This link is where all the audio transmission occurs, so you can use it to capture the user's first 10 seconds of speech. I'm not entirely sure, but I believe this method could potentially fulfill your use case.
Please note, I haven't tested this with a phone call to confirm whether or not a daily.co link is included in that webhook request, so you'll need to verify this.
Hi @Sahil , there is a request for an Daily.co API key when trying to access the room. This will need to be Vapi's API key right? What should I use there?