Indie singer Siddhant Goenka redefines music videos with AI innovation

Kolkata-based indie singer and super-tech star Siddhant Goenka invites his audience on a musical journey of discovery that goes beyond conventional boundaries and into the realm of artificial intelligence. Four out of six of his pop-rock music videos have a touch of artificial intelligence. Those who have seen the music videos are in disbelief. The 30-year-old artist gives an insight into the making of his music video and the incorporation of artificial intelligence.

Excerpts from the interview:

You are the first person in the country to make an AI music video? What inspired you to take this path?

I've always been curious and constantly looking for something new and different. It was a shot in the dark, but luckily it worked out beautifully for me. The journey started innocently enough. I noticed a gap in articulating my vision for song artwork when collaborating with others. To capture the mood and emotion I wanted, I decided to try it myself. In the process, I discovered an AI tool that played a key role in bringing my ideas to life.

Tell us about the process and your AI-inspired music video “Pari”?

I worked on the artwork for par and one night on my computer I created this ethereal figure in a white sari standing against the backdrop of an Indian graveyard. I had a eureka moment and thought, why not make this a full-fledged AI music video? So in November 2023 I released India's first AI-generated music video, par. I spent over 65 hours experimenting, learning and debugging. Horror movies and thrillers are a guilty pleasure for me, so inspiration struck and I had my princess, doomed to wander forever, wreak havoc on anyone who dares to love her. The story is truly scary, heartbreaking and intriguing.

Have you received any training in AI to be able to create music videos at this level?

I had no formal training, it was a lot of trial and error, but every laborious moment was worth it. Blurring the line between reality and AI to create something truly real. No cheat sheets, just tons of curiosity and countless YouTube tutorials with endless hours of learning. The results were fantastic. I was able to wear multiple hats without my creativity being limited. In one fell swoop, I was not only a musician, but also a director and screenwriter.

What apps did you use and how long does it take to create a music video?

I'll be honest: diving into AI tools like Midjourney, Kaiber, Runway and Leonardo was like navigating uncharted waters. JazbaatI needed about 7-8 hours to produce an abstract video. However, par was much more intense as I had to create lifelike people in different scenarios. My understanding of prompting improved with each project, allowing me to produce videos like Jaanley or Farishtey still requires at least 40 hours due to the detailed planning and editing of each scene.

What challenges did you face when creating music videos using AI?

First, it can be difficult to ensure that the AI-generated visuals match the mood and storyline of the song. Second, the learning curve for mastering AI tools is steep and time-consuming. Third, generating lifelike human scenarios and complex scenes requires a lot of time and fine-tuning, often taking over 40 hours per video. Finally, prompts and parameters must be constantly refined to achieve the desired quality and coherence, making the process both meticulous and challenging.

Still from “Farihyey” |

What is your songwriting and storytelling process?

My songwriting process is a deep dive into emotions where each lyric is a piece of my soul. I start with a melody whispering in my head and from there the words flow like a river of stories. Each song is a journey that blends personal experiences with universal themes of love, loss and hope. My storytelling weaves intricate narratives and paints vivid pictures. It is an alchemical process that transforms raw feelings into lyrical poetry with the aim of touching hearts and inspiring minds. All of this can be seen in the songs I released in 2023, namely Kacchi Raahon Pe, Jazbaat, par and in 2024 Farishtey, Jaanley, Alvida.

Do the lyrics of your songs generally express personal experiences you have had over the years?

When inspiration strikes, I truly believe I am being guided by a higher power. I often record melodies and lyrics on my phone. It's like there's a muse in my subconscious that constantly showers me with inspiration. So my songwriting draws heavily from personal experiences. For example: Kacchi Raahon Pe was born at a low point in my life when I needed motivation. It came out of nowhere and filled me with hope and happiness. On the other hand, Jazbaat was an attempt to capture the feeling of being trapped in a mental cage. The text, “Jazbaat so Gaye, neend se jaagey kyu kho gaye?” to capture this essence, while the bridge, “Chand sitaro ki zarurat hai, udney ki khwahish hai humne,” speaks to the inner fire that longs to touch the stars and symbolizes a rebirth of the spirit.

Still from “Farishety” |

In your latest music video, “Alvida,” you introduced elements of fire and brimstone raining down on a cemetery while musicians ply their trade surrounded by flames and lightning. How did you incorporate these ideas?

The idea came to me while I was working on this idea and thinking about a wild 'what if'. What if the artist himself is in deep agony? For us artists, the best way to express any kind of agony, anger, or even happiness is through our instruments, by creating melodies that scream in pain. We don't just vent our pain directly, we channel it through our music. This idea sparked something inside me. I love creating intense music videos, so I decided to give it a try. I still idolize the old school rock stars like Guns N' Roses, Scorpions, The Eagles, Elvis with their leather jackets, long hair, and beards. Hence, I got the idea that musicians in their outfits playing their instruments in a hellfire and brimstone environment would be impressive and intense.

The music videos you've made don't feature yourself. Do you plan on starring in a music video soon or creating an AI-generated music video featuring yourself?

I'm so glad you noticed my absence from my own music videos. I've been focusing on creating immersive cinematic experiences for my viewers in these three-minute music videos. The goal has always been to entertain the audience with the art that I'm ultimately creating from scratch. Lately I've been toying with the idea of ​​being the center of attention and I must confess that I have something in mind that I'm working on.

Do you think AI is the future when it comes to voice, music and music video creation?

AI tools are fantastic helpers to help artists bring their visions to life, but they can't replace the magic of the human imagination. Think of AI as the ultimate sidekick, as it can enhance and refine anything, but it's our unique experiences, emotions, and careful input that make the creative process truly special. While AI results can be shockingly impressive, you often notice that something is missing. Sure, it might get better over time, but we must always be innovating and pushing boundaries. After all, AI doesn't exist without humans, it's just our loyal assistant.

Still from “Farishety” |

If space permits:

What are you looking forward to in the future?

What really keeps me going is the incredible support of my listeners. Their kind words and constant encouragement push me to work harder. For me, building a community around my music is everything. The future holds exciting prospects as I delve deeper into the world of music. The endless possibilities often keep me awake at night with anticipation and drive me to strive for more, better and bigger. Going forward, I will ensure that every listener who has supported me receives only the highest quality music. As actor Shahrukh Khan aptly put it“Image abhi baki hai mere dost.”

Do you concentrate exclusively on music or do you also have a regular job?

Although music remains my primary interest, I am also interested in business and am an avid reader with a keen interest in the stock market. My days are carefully divided to dedicate time to each of these endeavors. This may sound exhausting, but my passion for all three things keeps me energized.

Still from “Jaanley” |

In each of these activities, I give my best and ensure undivided attention and excellence. This approach allows me to focus on the music and write only when inspiration strikes, rather than out of necessity. My endeavors in business and the stock market provide financial stability and allow me to support myself without being dependent on music sales. This independence allows me to be an artist in the truest sense of the word.

Balancing these commitments requires me to travel to three cities each month, a benefit of my multifaceted career. I am grateful to be able to dedicate time to each endeavor without compromising the integrity of any one venture. This balance is a testament to my dedication and passion and ensures that I can continue to be successful in all of my endeavors.