Spotify Pacer Mode
Use AI to find songs that you'd like to run to
Role
Feature Design
Full Stack
Product Ideation
Tools
Spotify API
Gemini
React
Platform
Web App
Tags
AI
Spotify
Proof of Concept
The Market Gap
My dad is an economist specialising in sustainable development. From ages 5 to 13, I lived in Korea and Laos where my dad served for international government agencies working with low income governments on how improving qualitiy of life and support infrastructure in different contries.
Visiting family in Los Angeles, moving to Vientiane, tagging along my dad's work trip in Jakarta, going off the boarding school in Massachusetts, or heading back to assignment in Seoul, life put me on the window seat of a flight for lots of my childhood. I wanted depict this part of my identity.
I started with drafting out the plane window in Figma. Since the ESP took Bezier curves, I thought the plane wing as viewed through the window in the format of an SVG would be a good representation.
Problem with existing BPM data
In essence, the idea behind the software would be to track/ask the user for a BPM target range based on their running, and find music that they listen to from their Spotify or Apple music account. However, the main problem that arises is in the current BPM databases.
Reputable BPM databases like Tunebat charge exorbitant fees (around $250/month) for API access to BPM data. This pricing model is prohibitive for independent developers like myself.
The alternative approach
To overcome these barriers, I explored an unconventional solution: using LLMs like Gemini 2.0 Flash and 2.5 Flash-Lite to search BPM data for songs. By providing the model with track names and asking it to ground its answers on a Google search, I was able to achieve surprisingly accurate results—about 96% accuracy in testing. This experiment demonstrated that public, AI-driven approaches can rival expensive proprietary databases for certain use cases. It also validated the potential for AI tools to democratize access to music metadata, opening new possibilities for personalized music apps without relying on costly or restrictive APIs.
User Flow
The Pacer Mode is designed as its own mini ecosystem, to provide a distraction-free listening experience. The goal is to provide a UI where the user can focus on their physical activity accompanied with the music that they like.
Main UI
The UI draws on the mental model of running tracking apps like Strava or UIs of treadmills:
Larger texts for legibility while physical activities.
Starting off with a pre-run count down screen, ending with a treadmill-like stop button.
Useful tracking meters like Time, MPH/KPH, and Miles
Although the Strides per Minute meter is one of the key features of this feature, the meter or the number figure itself does not provide utility to the user itself. Placing a medium-sized SPM meter (that also acts to indicate the next song) accompanied by the increase/decrease buttons, mirrors the UI of a treadmill where the user can click +/- buttons to increase the speed or inclination of the treadmill.
Learnings and Drawbacks
API restrictions from platforms like Spotify pose a major hurdle. Spotify impose limitations on API access, granting non-developer use only to apps with over 250,000 monthly active users. This makes it impossible for an independent developer like myself to ship a product that uses the Spotify API.
Potential Next Steps
Looking ahead, there are several promising directions for development. One is integrating cadence data from fitness devices like the Apple Watch, which tracks steps per minute (SPM), to dynamically match music tempo with running pace.
© 2026 Yunte Lee