Meet Varya AI, India’s new video generation model that can create stories from prompts
Avataar has launched Varya AI, a video story generation model designed for Indian users. Here's everything about its features, pricing, technology and availability.
Published By: Shubham Arora | Published: Jun 13, 2026, 12:35 PM (IST) | Edited: Jun 13, 2026, 12:44 PM (IST)
India is now looking to build more AI products at home, and Varya is one of the latest examples of that effort. Developed by Avataar with support from the IndiaAI Mission, Varya is a new AI model that can generate videos from simple prompts. The model was unveiled at an event in New Delhi in the presence of S. Krishnan, Secretary, Ministry of Electronics and Information Technology (MeitY), and Avataar's leadership team.
Unlike many AI video tools that are built for global use cases, Varya has been designed with Indian users in mind. According to Avataar, the model understands different aspects of everyday life in India, including regional cultures, festivals, food, clothing, public spaces, and local contexts. The company says the goal is to make AI-powered video creation accessible to a much larger audience, including students, teachers, businesses, and content creators.
What is Varya AI?
Varya is a video story generation model that lets users create videos using AI. You can type an idea, add an image if required, generate a video clip, and then continue adding more scenes to turn it into a larger story.
https://www.twitter.com/OfficialINDIAai/status/2065305077154447532
The company says the tool can be used across different scenarios, whether it is creating classroom content, making product ads, preparing informational videos, or putting together short visual stories.
The launch is also significant because Avataar was among the companies selected under the IndiaAI Mission to build indigenous AI capabilities using government-supported computing infrastructure.
How does Varya work?
One of the biggest talking points around Varya is the technology behind it. The model uses a technique known as distilled video generation.
In simple terms, most AI video models go through dozens of processing stages before generating a final video. Avataar says traditional video generation systems can require more than 50 inference steps. Varya reduces that process to just four steps while aiming to maintain similar output quality.
The company says this makes video generation significantly faster and more efficient without requiring the same level of computing resources.
What is distilled video generation?
Varya is built using a distillation technique. Without getting too technical, it allows a smaller AI model to learn from a much larger one and deliver similar results while using less computing power.
Instead of repeating every computational step, the smaller model learns shortcuts that help it produce similar results with fewer operations. According to Avataar, Varya applies this approach to video generation, reducing processing requirements while keeping quality at a comparable level.
Varya AI cost and pricing
According to Avataar's internal benchmarks, Varya can generate videos at approximately Rs 0.48 per second.
The company claims this makes the model up to 10 times more cost-efficient than several leading global video generation models currently available in the market.
The focus, according to Avataar, is on affordability and large-scale accessibility rather than simply building bigger models.
How to access Varya AI
Varya AI can currently be accessed through varya.avataar.ai.
Users need to sign in before using the service. Once logged in, they can enter their own prompt to get started.
The tool currently generates a 5-second video clip based on the prompt provided. Unlike most AI video generators that stop after creating a single clip, Varya lets you continue from where the previous video ends. So if your first prompt generates a scene, you can keep adding new scenes and build a longer story step by step instead of starting from scratch every time.
Here's how to use it:
The platform keeps letting you build on the previous output, which is why Avataar is calling it a video story generation tool rather than just a text-to-video model.
Get latest Tech and Auto news from Techlusive on our WhatsApp Channel, Facebook, X (Twitter), Instagram and YouTube.