Two production-grade projects: an open-source MCP server that hands any agent Sarvam's full API surface, and a real-time code-mixed voice agent for banking & financial services.
One gives every agent Sarvam's tools. The other puts them to work on a live, low-latency phone call.
Every turn runs through the same disciplined pipeline — instrumented, validated, and escalated when unsure.
Saaras v3 transcribes code-mixed audio; the router picks an intent and a model tier.
→RAG retrieves policy context; a groundedness guard blocks any answer not supported by it.
→Sarvam-105B calls validated backend tools; sensitive actions route to a human.
→Bulbul v3 streams the reply; cost, latency & PII-redacted memory are written.
Speech-to-text, reasoning, text-to-speech, translation and document parsing — all Sarvam models.