
What's your relationship with music while you work?
ElevenLabs has been building toward a music product for a while.
Two days back, they officially launched ElevenMusic, a platform that combines music generation, discovery, and a marketplace in one place.
It is free to try, available on web and iOS, and it does more than just generate songs from prompts, so I tested it.
But first, some catchup on AI this week:
TOOLS
1. Project Supermind: An operating system for your business that deploys 13 specialist AI agents across sales, finance, product, legal, etc, executing operations end-to-end with your approval before anything important moves.
2. Basedash: Describe what you want to track in plain English and Basedash builds a complete dashboard in minutes, including charts, KPIs, and reports from your connected data sources, without SQL. Supports 750+ integrations including PostgreSQL, BigQuery, Salesforce, HubSpot, and Stripe.
3. Wonder: An AI design tool where you generate designs, make precise edits, and work with your code context on the same canvas, as everything you create becomes the exact code you ship. Positioned as a Figma alternative for teams that want to go straight from design to production.
Setup
Go to elevenmusic.io or download the app on iOS. Sign up for free if you haven’t already.
You get seven song generations per day on the free tier.
When you land, you'll see a home feed with charts, new releases, and mood playlists. At the centre is a prompt window where you describe what you want to create.
Test 1: BG Music For A Yt Video Or Reel
Prompt 1:
"Upbeat lo-fi beat, no lyrics, good for a productivity YouTube video, around 2 minutes"
This came out really well, 10/10 for replicating the style.
It sounds exactly like the kind of lo-fi music you'd find playing on a YouTube livestream right now.
Prompt 2:
"Cinematic orchestral, no lyrics, for a travel montage reel, 60 seconds"
Decent, but not quite what I expected.
I was looking for something faster-paced, closer to that dreamy movie-brain aesthetic you see on Instagram reels. This didn't quite get there.
Still usable if you pick this as your track and cut your video to match it, it works. But the gap between what I visualised and what came out was noticeable.
A few things you can adjust after generating:
Length (slider from 30 seconds to 4 minutes)
Lyrics on or off
Writing style / genre
Test 2: Custom Intro Track For A Podcast
Prompt:
"Short podcast intro, 20 seconds, electronic with a warm feel, no lyrics, builds to a clear ending"
It's extremely simple and doesn't sound electronic at all despite the prompt.
It's decent in the way that one of twenty MKBHD videos might use something like this as background.
But most podcast intros you'd remember are more energetic, hooky, and catchy. You listen and you don't want to click away.
This doesn't invoke that, so I came out underwhelmed.
Test 3: Remix Someone Else's Track
Go to the Discover or Charts tab and browse until something catches your ear.
Open a track and you'll see a Remix option.
Before we get there though, in the marketplace we can buy tracks with credits. I found a really nice electronic track someone had uploaded, bought it, and then remixed it.
The credits system is a nice touch as it smooths out the experience of exploring the marketplace.
Remix prompt I used:
"Same tempo and vibe, but make it feel more melancholy. Less bright, more late-night."
It followed the prompt but I'm not sure I'm happy with the output.
The original had something, which the remix preserved but lost whatever made it feel interesting.
Hard to say if that's the tool or the prompt.
One thing to know: remixes count toward your seven daily generations.
My Take
I kept coming back to is how iterative this is.
What you're imagining and what comes out are going to be different, sometimes very different.
That gap isn't new as we've all been through it with text, images, and video. And we learned over time how to prompt better and make it work.
Music exposes that gap all over again.
I think it's going to take a while for us to figure out how to get the kind of music we want out of these tools.
That said, I'm fascinated by ElevenMusic as a platform.
Visual AI media has had most of the attention so far and AI music still feels underexplored.
And music is where more people will find a reason to engage with this, because everyone has a relationship with music.
Everyone has taste, preferences, a sound in their head. That makes the exploration more personal and the possibilities more diverse.
So, it’s worth trying.
Go to elevenmusic.io, and reply to this email with a link to something you make.
Until next time,
Vaibhav 🤝🏻
If you read till here, you might find this interesting
#AD 1
ChatGPT gives you generic answers because you give it generic prompts.
You know the fix: longer prompts, more context, clearer constraints. But typing all that takes five minutes per prompt, so you shortcut it. Every time.
Wispr Flow lets you speak your prompts instead of typing them. Talk through your thinking naturally — include context, constraints, examples — and get clean text ready to paste. No filler words. No cleanup.
Works inside ChatGPT, Claude, Cursor, Windsurf, and every other AI tool. System-level, so there's nothing to install per app. Tap and talk.
Millions of users worldwide. Teams at OpenAI, Vercel, and Clay use Flow daily. Free on Mac, Windows, and iPhone.
#AD 2
Protect Client Trust in Volatile Markets
When markets get shaky, advisors don’t just manage portfolios. They manage a surge of client emails, questions, and last-minute meetings. BELAY’s free Financial Advisor’s Delegation Guide shows how better delegation protects responsiveness, reduces bottlenecks, and helps your firm stay client-facing when pressure and volume rise fast across the entire firm.













