How We Used Suno AI to Turn Human-Written Lyrics Into a Memorable Melody

At Sixteen By Nine (SBN) Media, when we started work on our first AI music video, we began with a creative vision and a specific objective: Can we create an AI music video where every element, including the lyrics, composition, arrangement, and visuals, felt intentional and authored?

More specifically, could we write human poetry, then use AI music generation to match that poetry's emotional texture so perfectly that the composition would feel as if it were written specifically for those words?

Watch Rang-E-Yaad:
https://sbnmedia.in/the-making-of-rang-e-yaad-a-cinematic-ai-music-video

The Lyrics

Rang-E-Yaad’s lyrics were written by a human writer, and the music composition followed from those lyrics. This matters because the emotional intelligence of the song is entirely human.

The song opens with:

इश्क़-ए-जान कोई गिला नहीं, दिल है कहीं और जान कहीं। एक दूजे के ख़ातिर हैं कहाँ, रंग-ए-याद फिर आई नहीं।

These lines carry the weight of a love that has quietly separated. The heart is somewhere. The soul is somewhere else. And the colour of memory, rang-e-yaad, refuses to return.

The title itself, Rang-E-Yaad, translates to "the colour of memory." It became the thematic anchor for every visual decision we made.

Building the Story

The song speaks of two people separated, of a love that has not died but has been quietly shelved. The question was: why are they apart?

We landed on one of the most universal situations a person faces, the moment when life choices, career, ambitions, or the next chapter pull someone away from the person they love. Not a dramatic breakup. Not a fight. Simply two people whose paths moved in different directions at a defining moment.

That relatability became our guiding principle for the narrative. We wanted viewers to see the story and immediately understand the emotional geography without it needing to be spelt out.

Music Production: Suno AI as Composer and Sound Architect

With the lyrics and story locked, the audio production began. The music, the composition, and the arrangement of the song were produced entirely using Suno AI.

The instrumentation supports the quiet longing of the song rather than overwhelming it. Getting this right required iterative work. After multiple iterations, we landed on the melody and song arrangement we were looking for.

The Visual-Audio Synchronisation

Most AI videos look plastic and lack human emotion. These videos generally are a montage of a character in different situations and locations, which generally do not match the song's narrative or story. These, coupled with character consistency and acting issues, are the key reasons why most AI videos are not received well by audiences.

We wanted to change this. We wanted to create an AI music video where the music and visuals work as a cohesive unit, with each element amplifying the other's emotional impact.

We produced Rang-E-Yaad end-to-end in-house, controlling both the music layer through Suno AI and the visual layer through Google Veo 3.1. This allowed us to develop the project holistically rather than fitting music to pre-generated visuals or adapting visuals to existing music.

And we did not stop here. We knew that in order to make the audience connect with the song and the music video, we had to make the AI character sing. Not just sing but sing with emotion, that too with perfect lip-sync with the song tune.

Making an AI character lip-sync to a song tune is fundamentally different, and exponentially harder, than making a character speak standard dialogue.

In spoken dialogue, if an AI character pauses for a fraction of a second too long, it can easily pass as a natural, dramatic breath. In a music video, the audio track is fixed and inflexible. The tempo, rhythm, and beat are locked. You cannot bend the audio to fit the video.

While making the protagonist sing in the music video, we matched his lip movement, emotions, and singing performance to every pause and nuance of the song tune perfectly.

The final result is a performance that holds up to the closest scrutiny. The character’s mouth movements, pauses, and emotional expressions feel completely in tune with the song.

The Result: Music That Actually Stays With You

When you listen to Rang-E-Yaad, it sounds like a song written for these specific words by someone who understood the emotional landscape.

The composition carries the weight of the narrative without overwhelming it. The melody is memorable enough that listeners find themselves recalling it after one listen. The arrangement respects the poetry. The pacing allows space for reflection. And most importantly, people do not notice that the video and the song are made using AI tools.

What This Means for Your Upcoming Music Videos

If you're exploring AI music video production or considering how to use AI in your workflow, SBN Media can be your ideal production partner.

At SBN Media, we believe that AI-generated content should meet the same standards as traditionally-created work. It should be memorable. It should be emotionally intelligent. And it should feel intentional.

Rang-E-Yaad is proof that when you approach AI tools with intention, iteration, and serious creative thinking, the output stands out.

Start your next AI music video with SBN Media today.