Introducing Arth V2, SquadStack's in-house streaming speech model, built for India's phone calls 🧵 At 67 ms, it's the fastest model that outpaces every engine and beats Sarvam, Deepgram, Google and OpenAI on accuracy across 863 real Indian sales calls.

Our AI agent did its homework before this seller even picked up. It knew what he sells, where his shop is, how many buyers want products like his and where they are, what a typical order looks like, and how many enquiries similar sellers nearby are getting.

Voice AI pricing in India today looks like BPO pricing. Vendors compete on cost per minute. Buyers compare rate cards. Everyone is negotiating an input. No lender walks into a board meeting and says “we bought 4 lakh minutes of voice AI this quarter”. They bought disbursals. Insurers bought renewals. Universities bought enrolments. Cutting calling costs by 60% saves about 2% of revenue. Lifting conversion by 10-15% adds 10-15% of revenue. The industry has been pricing on the wrong number. Today we announced outcome-based pricing for our Voice AI sales agents. A low fixed base to run the agents, and a success fee on the revenue they create. We don't sell voice AI. We own a line in our customer's MIS. economictimes.indiatimes.com…

Day 5 of 5: Introducing Inline PII Redaction @SquadStackAI redacts customer PII in real time, before it reaches the LLM. The calls that drive the most revenue in BFSI are the ones where customers speak Aadhaar numbers, PAN, bank details out loud. In most voice AI systems, that data sits in plain text across the full stack. STT output, transcript, LLM prompt, model provider's API, logs, QA dashboard. No redaction at any step. The hard part: PII on voice calls doesn't arrive in one clean line. A customer spells their PAN across four turns. They switch between Hindi and English mid-sentence. Single-turn detection misses most of it. So we built inline PII redaction, a 6-turn rolling window between the STT engine and the LLM that catches PII split across fragments. 16 entity types, tuned for Indian voice conversations. A regulated brokerage's compliance team recently reviewed this and signed off for production at scale. To learn more: squadstack.ai/blog/why-your-…

Day 4 of 5: Introducing RAG & Context Management Your AI agent can now handle long complex calls without a human stepping in! A few weeks ago I wrote about how we fixed 20-minute long revenue calls. How the agent could remember everything the lead said and hold up! Remembering wasn't enough on its own. In some instances, the agent just couldn't reliably answer the very hard and specific product question the entire call was building toward. Not because the knowledge was missing. Every policy detail, pricing sheet, FAQ was loaded into the prompt. The prompt was just so heavy that the model skimmed past the exact answer the caller needed. So we moved product knowledge out of the prompt entirely, and put it in a knowledge base. The agent reads from it, only when the caller asks. Retrieval takes under 100 milliseconds. On blind tests, including an 87-page product manual, it finds the right answer 97% of the time. Context Management gave the agent memory. The knowledge base gives it depth. Together, the 20-minute insurance call, the loan advisory call with fifteen branching questions, now close without a hiccup or the need of transferring to a human. Full story: squadstack.ai/blog/launching…

Day 3 of 5: Introducing Overwatch A question I hear from leaders running voice AI at scale: how do we know what's actually happening on the calls? The most expensive problems never throw an error. If the greeting has a two-second lag, or the agent fumbles a rebuttal on a specific objection, or it marks a lead as qualified without capturing the right entity. You find out days later, when the numbers slip. That's why we built Overwatch. A call slows down? Overwatch tells us whether it was the STT, TTS, LLM, or a tool call. A campaign stops connecting? We see the telephony vendor, the drop reason and the DND status before anyone files a ticket. A metric spikes? You go straight from the number to the exact calls it touched, by ID, ready to open and listen to. Every problem you miss on the first call repeats on the next thousand. At ten thousand calls a day, seeing it early is the difference between scaling and quietly leaking revenue. Overwatch is now live inside our Humanoid Voice AI Agent. Full story here: squadstack.ai/blog/introduci…

Day 2 of 5: Introducing Vernacular Voice AI Agents Every voice AI platform lists a dozen Indian languages on the feature page. The count keeps climbing. But deploy these agents in production and the conversations fail. The agent speaks “correct” Tamil. It sounds like a textbook. The customer knows in three seconds. They hang up. We found that naturalness splits roughly 20/80 between TTS configuration and dialogue engineering. The 80% is the part nobody wants to do. We mine fillers from real human agent calls, test every filler against every voice on real 8kHz telephonic calls, maintain a kill list of phrases that signal AI, and write every line of dialogue by hand. No LLM generates this. That's the point. We've launched vernacular voice AI agents across India's top languages. They’re live across large-scale enterprise campaigns. We wrote about how we built it: squadstack.ai/blog/supportin…

Day 1 of 5: Introducing Lift In voice AI, the agent that improves fastest wins. Today we're introducing Lift, the self-improvement layer for our Voice AI Agent. It learns from every call and makes the next one better. The result is a conversion rate that keeps increasing, with no one rewriting the prompt. Five years of running contact centres for India's largest brands taught us exactly where a call leaks conversion. Lift puts that to work. It analyses live calls, finds the changes that lift conversion, and proves it on live traffic before it scales, so nothing reaches full volume until it has beaten the current agent head to head. We're already running it in production, and the results are holding up across campaigns. Work that took a team weeks now happens in hours, so the agent reaches its best far faster, and stays there as objections shift, offers change, and new patterns surface in the calls. Building the agent was only ever the start. Keeping it at its best, on every call, while everything around it keeps changing, is the real work. That's what we built Lift to do. Learn more here: squadstack.ai/blog/introduci…