Here's how webhooks work in Vaani (no code needed)
A webhook is just Vaani sending your app a message when something happens on a call.
You pick the events you care about: call_started, call_ringing, user_picked_up_at, call_rejected, call_no_answer, call_failed, call_ended.
You give us a URL. When a call ends, we send it a message, and you can drop the result in a Google Sheet, ping Slack or update your CRM.
Hey Product Hunt 👋
I’m Chandra from Vaani, a small voice AI team in Bengaluru.
Voice AI started with great models and only later got applications, so putting an agent on a real phone line still means stitching together speech, an LLM, telephony, tools and retries. We built an internal tool to configure agents without all that glue. Founders, PMs and developers who saw it kept asking for access, so today we’re opening it up.
What you can do, no code:
Design the call flow, including how the agent handles objections, interruptions and edge cases
Give it actions: hold, schedule a callback, hand off to another agent or a human
Connect a knowledge base so it answers from your docs mid-call
Pick a number and go live
After every call, get structured data: extracted fields and a disposition, so you don’t have to read transcripts to know what happened
It also orchestrates multiple models and switches to a backup if one fails mid-call, so one bad response doesn’t wreck the conversation.
We started with languages where data is scarce, which is why “sounds local” matters so much to us. It’s built to work for your customers wherever they are.
What’s the first voice agent you’d build, and what would you expect to break it?
We’ll be in the comments all day.
Try out the platform first-hand at https://platform.vaani.dev/
Grab 1000 free credits by using the code PH100x
@chandrashekran_y I'd build a "call my notes" agent.
Call a number, ask what I decided about a project last week, get an answer from my docs without opening five tabs.
What I'd expect to break it: me switching between Hindi and English halfway through, then interrupting to correct a name. That's a pretty normal conversation, but a messy test case.
Also curious about the fallback: if the model switches mid-call, does the new one retain the full context, or does the caller have to repeat themselves?
@maybe_someone_20 We actually built this platform for curious techies like you,
Cant wait to see how your built goes, do share a feedback and love if posssible!
And reg. your question, absolutely, the agent context is preserved independant of the models at play
How well do you guys handle people switching between hindi, english and regional languages mid-convo, like we naturally do in India?
@nishank_koul haha, this is one of the first problem statements we started out with,
To be very frank, We treat language as a probability n not a setting, Vaani.dev tracks context across turns to predict switches and mixing patterns, or you can lock a languages by config when you need strict control.
Vanni works for the vernacular languages too?
@avirup_sarker Absolutely, Low resource languages is one of our biggest strengths, would love for you to try it and let us know how it goes!
we built the voice AI infrastructure. now it's your turn to break things.
@mohammad_palla2 absolutely, cant wait to see the crazy use cases folks gonna be building on Vaani.dev
when the agent calls to an iphone user the screening assistant may respond to the call , leading to a agent to agent conversation and unnecessary cost.
Can we handle this in vaani
How does it deal with people interrupting the agent, or speaking before it is done with its response?
@manik_singhal1 haha, this is a classic problem buddy, more our agents naturally handle, but better, we hand out these control and control to the users, you can control exactly how the agents need to behave and calibrate it based on the use case!
@Vaani Developer Platform is the easiest platform for building voice agents!
@daksh_goel glad that you liked vaani dev platform. Pretty excited for what you build next with Vaani