VARTA architecture
VARTA splits a voice agent into two halves. DAKSH does the slow, language-specific LLM work once, before any call, and writes it down as workflow data. The turn engine reads that data during the call with rules first and the LLM last, so most turns are answered in microseconds from pre-built audio.
Runtime · call time
VARTA Engine Architecture
How VARTA runs a live voice-agent call — a fixed cascade of rule-first layers with Hindi names, where the LLM is tried last and pre-built audio clips answer most turns.
Authoring · design time
DAKSH Architecture
How DAKSH turns an author's brief, pasted spec or one-line edit into a validated voice-agent workflow — steps, rules, language data and pre-built audio — so live calls need no LLM for any of it.