Right now, when you use for example deepgram with your own keys, you are forced to use your own keys both on STT and on TTS. In this particular case, as an example, it is better to use it just on STT but make use of vapi.ai TTS keys. Is there any way to select which credentials to use in an assistant? Or any way to disable the usage of that credential in one kind of product (TTS, STT...). Thanks.

Hi there, Thank you for your message. Our team is currently out of the office. We operate Monday through Friday, from 9:00 AM to 8:00 PM Pacific Standard Time (PST). We’ll get back to you as soon as possible during our normal business hours. If your message is urgent, please mark it accordingly or include “URGENT” in the subject line, and we’ll do our best to respond promptly. Warm regards, Vapi Customer Support Team

Thank you for your question! Based on the documentation, you can add and manage provider API keys (like Deepgram for STT) in the Vapi dashboard, and you can configure different providers for models and voices in your assistant setup. However, it is not explicitly documented whether you can use your own API key for only STT while using Vapi's (or another) key for TTS within the same assistant. To better assist you: Are you looking to configure this at the assistant level (per assistant), or do you need to set different credentials for STT and TTS within a single assistant configuration? Let me know your exact use case, and I can help you further! Source: - [Provider Keys](https://docs.vapi.ai/customization/provider-keys)

I would like to use my own keys with Deepgram just for STT, but use vapi for TTS. I don´t mind the way to achieve it.

Yes, as long as you have a key entered in for deepgram, you will only use the API keys that you have entered.

Yes, but would it be possible to use that API Key only deepgram stt and not using it for deepgram tts?

We apologize for the delay in responses lately. We are in process of making some changes to our workflow in how we handle support requests. The good news is that we are starting to get back on track of having a 48 hour response time and we would like to start cleaning up anything old. With that being said, just wanted to check in with you to see if you have made any progress or changes to your project since support has last reached out.