How I Used Sarvam AI’s Free API to Clone My Friend
Last Updated on February 21, 2026 by Editorial Team
Author(s): Shashwat
Originally published on Towards AI.
Why spend $20 on OpenAI when you can build a hyper-local, Hinglish-speaking roast bot for ₹0 using India’s newest LLM?
This morning, I was staring at a Kubernetes deployment where the helm kept reconciling (brb, crying)
The article discusses the author’s experience using Sarvam AI’s free API to create a localized chatbot that captures the essence of a specific friend, highlighting the importance of context and slang in AI modeling. It emphasizes that a smaller, specialized model can sometimes outperform larger, generic ones when tailored to specific cultural nuances. The author encourages readers to experiment with building their own versions, reflecting on the efficiency and effectiveness of Sarvam AI for local challenges.
Read the full blog for free on Medium.
Join thousands of data leaders on the AI newsletter. Join over 80,000 subscribers and keep up to date with the latest developments in AI. From research to projects and ideas. If you are building an AI startup, an AI-related product, or a service, we invite you to consider becoming a sponsor.
Published via Towards AI
Towards AI Academy
We Build Enterprise-Grade AI. We'll Teach You to Master It Too.
15 engineers. 100,000+ students. Towards AI Academy teaches what actually survives production.
Start free — no commitment:
→ 6-Day Agentic AI Engineering Email Guide — one practical lesson per day
→ Agents Architecture Cheatsheet — 3 years of architecture decisions in 6 pages
Our courses:
→ AI Engineering Certification — 90+ lessons from project selection to deployed product. The most comprehensive practical LLM course out there.
→ Agent Engineering Course — Hands on with production agent architectures, memory, routing, and eval frameworks — built from real enterprise engagements.
→ AI for Work — Understand, evaluate, and apply AI for complex work tasks.
Note: Article content contains the views of the contributing authors and not Towards AI.