I have an agent execution platform based on the google ADK which takes the input from the user and respond via a REST endpoint. Now I want to add voice to this setup. Im expecting vapi to take the voice from the user transcribe and give me a callback and then transform the response text back to voice and talk to user. Not seeing a mechanishm to do this as of now. I tried to use the reactSDK and created assistants on the fly. Idea was to create a basic agent which handles the conversation and adding my agent execution end point as a tool and then prompt the assitant to call the tool always. BUt I am not able to add tools for the dynamically created agent. When I mention the 'tools' property, the vapi is throwing an error 400 .

Create your tool in Vapi dashboard to get a valid toolId, then use the assistant-request webhook to dynamically return assistant JSON that includes this toolId; instruct the assistant to call the tool via prompt, handle the tool call on your server by hitting your agent’s REST endpoint, and return the response as text for Vapi to convert back to voice..

Thank you for the response. As I mentioned I have a system which is backed by ADK and it will be creating dynamic agents from my json definitions and running. I.e, I will be invoking various types of agents based on the agent id (the endpoint is somewhat like ../agent//run ) . And this can be from various environments like, staging/prod etc. with tenantId, appId , userId etc. And auth is additional. So I was thinking adding persisted resources can be a bit difficult to manage - > create , manage, purge etc. If they are lightweight transient configurations and will be available only for that session , that whould've helped. Also, My use case is basically just to add voice layer on top of the existing chat framework and tap the phone capability of the vapi too. Can you please suggest the best implementation model for this ? if possible few references too .. thank you.

Hi, First off, we want to sincerely apologize for the delay in getting back to you. We understand how frustrating it is to wait - especially when you're counting on us - and we owe you a clear explanation of what’s been happening and how we’re addressing it. Over the past few weeks, we've seen a significant increase in support requests. While this reflects exciting growth, it has also stretched our small team and exposed some real challenges in scaling our support operations. To improve your experience, we’ve taken a step back to reassess our approach. Here’s what we’re implementing: - Smarter Support Through Automation: We’re investing in our AI support systems to help you resolve issues more efficiently. Soon, our support bot will offer expanded capabilities, making it easier to access accurate, instant help—particularly for common or repetitive queries. - Expanding the Support Team: To meet growing demand, we’re adding 2–3 new team members focused on managing support volume and improving response times. - Prioritized SLAs for High-Usage Accounts: We’re introducing service level improvements for users who are growing with us: - Accounts with usage over 1,000 minutes/month will receive prioritized support. - For all general inquiries, we’re establishing a standardized 48-hour response time. We’re confident these steps will lead to faster, more reliable support and help us better serve you as you grow with us. Also, in case you still need help with this ongoing ticket, do let us know, and we will help you get this resolved as soon as possible. Thank you for your continued patience and for being part of our journey. Warm regards, Vapi Team