Meet the Indian sibling duo behind Koyal, an AI-enabled platform that converts audio into a full movie

Discover how Indian siblings Mehul and Gauri Agarwal seek to transform the landscape of filmmaking with Koyal, a groundbreaking platform that converts audio into cinematic videos, enabling creators to visualise their stories without hefty production costs. 

Gulam Jeelani
Updated11 Sep 2025, 11:30 AM IST
Mahul, 23 and Gauri Agarwal, 26, computer science graduates are based out of San Francisco Bay Area, California
Mahul, 23 and Gauri Agarwal, 26, computer science graduates are based out of San Francisco Bay Area, California

In 2019, Mehul Agarwal would do stand-up comedies when he was studying computer science at Carnegie Mellon University (CMU) in Pittsburgh, Pennsylvania. Agarwal would think of converting his jokes into a film without having to bear the production costs.

On 9 September, Agarwal announced the beta of Koyal.AI, the audio-to-video filmmaking platform, on his LinkedIn. Koyal is the fastest and the best way to go from your audio to cinematic video with consistent characters, settings and storylines, Mehul and his sister and co-founder Gauri Agarwal told LiveMint in an interview.

Also Read | China shares climb on AI optimism despite US drug restrictions

“It's perfect for anyone with a lot of audio - musicians, podcasters, or storytellers of any kind. Turn your music to music videos, podcasts to TV shows or bed-time stories to animated films,” says Agarwal, 23.

‘Barbie movie in a castle in Northern Ireland’

Using Artificial Intelligence (AI), Koyal generates custom characters and animations in minutes while giving users creative control. Creators can also make personalised avatars, change scenery, makeup and costumes, and even edit the tone and mood of the dialogue.

For example, Mehul explained during the virtual interview, Koyal can set a scene from the “Barbie” movie in a castle in Northern Ireland or create a bespoke music video with a choreographed flash mob.

The product’s suite of tools helps the user’s imagination come to life in minutes, he says.

The WAVES experience

Koyal, a next-generation GenAI audio-to-video storytelling platform, was seen live in action in a series of music videos launched during the inaugural day at the World Audio Visual and Entertainment Summit (WAVES) 2025 in Mumbai in May this year.

This unique platform lets users generate personalised narrative-driven videos from their audio in a variety of engaging styles. “It transforms audio tracks into rich, emotive video narratives using state-of-the-art AI models that extract emotions, context, and storytelling elements directly from music,” said, Mehul, who is 23.

AR Rahman, Shankar Mahadevan, and many more…

Mehul says that renowned playback singer and composer Shankar Mahadevan and Music maestro AR Rahman have collaborated with Koyal before the public beta version of the platform was out this week. The collaboration with Mahadevan and Rahman was while making and supporting the video creation for the Waves Album. It also featured artists Ricky Kej and Meet Brothers, he says.

The founders said that with its multimodal AI suite and state-of-the-art character consistency, Koyal is setting new benchmarks for how artists and creators visualise their work.

Also Read | Shah Rukh Khan speaks about respect for women; netizens call him ‘Mehenga Babil’

'The product is rooted in our research paper presented at NeurIPS 2024 AI conference and our patented secure personalisation protocol CHARCHA, which ensures video personalisation happens only with user consent," said Gauri, 26.

NeurIPS is a machine learning and computational neuroscience conference held every year. The 2024 version was the 38th annual conference on Neural Information Processing Systems held at the Vancouver Convention Centre, Canada, in December 2024.

“If users want their likeness to appear in the video, they can use the CHARCHA verification steps to create a personalized avatar. But users can also choose not to incorporate their likeness and instead only use generated models. We developed CHARCHA to be available as a safeguard to prioritise consent,” Gauri said.

CHARCHA stands for Computer Human Assessment for Recreating Characters with Human Actions.

Computer Science Graduates

After schooling in India, Mehul earned his master’s degree at the Robotics Institute (RI) in 2024 at Carnegie Mellon University in Pittsburgh, and Gauri Agarwal completed her bachelor’s degree in computer science in 2020 before continuing her studies at the Massachusetts Institute of Technology (MIT).

In between, Gauri has also worked with Meta (then Facebook) for three years in the Instagram reel generation section, before the brother-sister duo started working on KoyalAI.

Through their programs at CMU, the Agarwals connected with Jean Oh, an associate research professor in the RI, and Michael Hilton, a teaching professor in the Software and Societal Systems Department, leading to the collaborative development of Koyal, the university said in a statement on 9 September.

"Until now, we have only worked with enterprises. Now we are public. Anyone can use our platform and make videos. Our hope with Koyal is that it broadens opportunities for a range of creators, not just those who can afford large-scale production. AI is moving fast, and we are providing a safe way to explore its potential," said Gauri.

It's perfect for anyone with a lot of audio - musicians, podcasters, or storytellers of any kind.

The Agarwal siblings live in the San Francisco Bay Area, California, in the United States.

Also Read | Artificial intelligence’s next home: your eyes

"We worked with seven paid pilots with India's biggest music labels, podcasts and storytelling companies, and have now launched the prosumer product. We recently concluded a pilot with Universal Music and T-Series alongside Bollywood production houses like Maddock Entertainment, and Collective Artists Network," Mehul said adding, ‘I can happily use this to make a movie out of my stand-up jokes.’

Key Takeaways
  • Koyal empowers creators by transforming audio content into engaging videos.
  • The platform utilizes advanced AI models for personalized storytelling.
  • The Agarwal siblings' backgrounds in computer science and machine learning play a crucial role in Koyal's development.
Get Latest real-time updates

Catch all the Business News , Corporate news , Breaking News Events and Latest News Updates on Live Mint. Download The Mint News App to get Daily Market Updates.

Business NewsCompaniesPeopleMeet the Indian sibling duo behind Koyal, an AI-enabled platform that converts audio into a full movie
More
OPEN IN APP