Build a voice agent that sounds and behaves human without writing a single line of code. Design the call flow, handle objections and edge cases, connect your tools and knowledge base, and go live on a real phone number. Every call ends with clean, structured data.
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 PHL1000X
Really interesting approach to voice AI. I like that Vaani goes beyond just building the agent and considers the entire call experience, from handling interruptions and edge cases to getting structured data after each call. The model failover is also a nice touch. Great work👏.
What options does Vaani have for deployments? I want to embed a chat/voice bubble on my website. Can I do that with Vaani?
@Vaani Developer Platform experience is something which lacks a lot during an AI call, how that would be handled properly like .... asking key validation to ensure its you and putting your call on hold to check the vital info, earlier in human calls there was a hold tone and an apology ... but in AI its a long pause and slow conversation which frustrates user...
How that is gonna handled .
a friend's company trialed with every top voice AI startup in india to automate renewal calls. they picked the company’s revenue depends heavily on renewals. most of the non startup Top 500 companies of India are their customers. renewals here happen on phone calls, not card subscriptions. they went with vaani because of good the tech is, and also because the team stays with you until you're happy.
Not just another voice ai platform! Love all the features offered and the story of customer first build!
I have seen Vaani grow from an api to now a platform. Crazy growth & cracked team is building something very useful for India & the world!
Go check it out. 🚀
Congratulations on launch! I have two questions
How does it handle interruptions from the speaker?
How does it handle cases where the other side is an IVR or even more challenging, another AI?
Been exploring vaani.dev and genuinely love what the team is building. Making voice AI accessible to anyone is a big step. Excited to see where this goes!
The post-call structured data is what caught my eye. How do you handle it when a caller gives a partial or contradictory answer — does the extracted field get flagged as uncertain, or does it just pick one value? Curious how that plays with the disposition you assign.
How are you different from Telnxy or Twillo or Eleven Labs?
Are you also competing in the markets of Arrowhead, Samora, Bolna etc?
Very cool tho!!
In India, people switch between English and local languages pretty quick within the same call 😂 Does it automatically handle that?
been rooting for Vaani since day 0, and it’s been incredible to watch this product come to life!
@thestartupkid1@chandrashekran_y@bhavya_singh11 and the entire team have put in so much effort, countless iterations, and late nights to get here. from the early days of building to finally launching on Product Hunt, so happy to see all that hard work come together. you guys deserve all the love and support today!
lesss gooo, team Vaani!
About Vaani Developer Platform on Product Hunt
“The only voice AI harness that you'll ever need”
Vaani Developer Platform launched on Product Hunt on October 30th, 2026 and earned 370 upvotes and 108 comments, earning #1 Product of the Day. Build a voice agent that sounds and behaves human without writing a single line of code. Design the call flow, handle objections and edge cases, connect your tools and knowledge base, and go live on a real phone number. Every call ends with clean, structured data.
Vaani Developer Platform was featured in Artificial Intelligence (482.7k followers), Tech (635.9k followers) and Audio (2.2k followers) on Product Hunt. Together, these topics include over 311.2k products, making this a competitive space to launch in.
Who hunted Vaani Developer Platform?
Vaani Developer Platform was hunted by Rohan Chaubey. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Reviews
Vaani Developer Platform has received 1 review on Product Hunt with an average rating of 4.00/5. Read all reviews on Product Hunt.
Want to see how Vaani Developer Platform stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Rohan Chaubey
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 PHL1000X