Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Feels: Translating Your Spotify Soundtrack into Real Outdoor Places with Local AI and SerpApi

Description and use

Feels translates a user’s recent Spotify listening session into curated outdoor destinations that match the music mood, encouraging users to step outside and reduce screen time.

Problem

Developers spend long hours in front of screens, and Spotify’s autoplay queues reinforce this behavior, keeping users indoors.

Outcome

The Feels app translates a user’s recent Spotify listening session into three outdoor destinations that match the music’s mood, encouraging users to step outside and reducing screen time.

Workflow

  • Authenticate with Spotify via OAuth 2.0 (user-read-recently-played).
  • Fetch the ten most recent tracks once per day and store them in a local SQLite database.
  • Run the Qwen 2.5 Coder 7B model locally through Ollama to analyze tempo, energy density, and emotional descriptors, outputting a JSON schema.
  • Translate the model output into spatial search queries and query SerpApi’s Google Maps engine for verified outdoor destinations.
  • Present three curated destination cards with ratings, reviews, photos, and one‑click Google Maps directions.
  • Enforce a 15‑refresh‑per‑day limit to keep screen time minimal.

Evidence

Feels is a web application that takes your recent Spotify listening session and interprets its acoustic cadence, energy density, and emotional texture using an open-weight model running locally on your hardware.

Source

It maps your sonic state to geographic search intents, then uses SerpApi's Google Maps engine to find three verified real-world outdoor destinations.

Source

The application enforces a strict cap of 15 refreshes per day.

Source

  • Record date: 2026-10-09T22:56:02.610Z