Skip to content
← Projects

Echo Echo

An AI music generation platform — multi-agent LLM orchestration (CrewAI + Groq Llama 3.1) composes 30-second instrumental sketches via the Suno v4 API, generates thematically aligned lyrics, and scores every output through an automated copyright-similarity detection pipeline.

Built by

PythonFastAPICrewAIGroq Llama 3.1Suno v4 APIThree.jsRender

Overview

Echo Echo is a full-stack AI music generation platform that turns mood, genre, tempo, and free-text prompts into original, copyright-safe instrumental tracks. A multi-agent LLM pipeline handles composition, lyric writing, and copyright risk scoring end-to-end — from a guided 8-step generation flow in the browser to a downloadable MP3/WAV with a shareable public link and QR code.

Architecture

  • FastAPI + Uvicorn backend exposing async REST endpoints for generation, library management, and auth
  • Multi-agent orchestration with CrewAI — specialized agents powered by Groq Llama 3.1 handle lyric composition and thematic alignment against the user's mood/genre/theme inputs
  • Music synthesis via the Kie.AI (Suno v4) API, producing ~30-second instrumental sketches in real time
  • Automated copyright-similarity detection — every generated track is scored against known material before it reaches the user's library
  • Vanilla JS frontend with Three.js for 3D visuals; guided step-by-step generation UX (mood → genre → tempo → prompt)
  • Invite-only authentication with email/password login
  • One-click Render deployment via render.yaml with environment-based configuration

Features

  • 8-step guided composition flow with 17+ genres and mood/tempo presets
  • Personal track library with playback, trimming, download (MP3/WAV), and play history
  • Shareable QR codes and public links per track
  • Real-time "now composing" generation feedback
  • Tiered usage plans (free monthly generations through unlimited)

What It Demonstrates

Integrating multiple third-party AI APIs behind one coherent product: agentic LLM workflows, generative audio, similarity scoring as a safety layer, and a deployed, auth-gated product UI — all shipped on cloud infrastructure.

Related projects

Noloop

A glass-box medical claims adjudication and fraud-defense platform — an AI agent pipeline turns unstructured claim documents into explainable, role-specific decisions for patients, hospitals, and insurers.

RAG Document Assistant

A production-style Retrieval-Augmented Generation system — documents are chunked, embedded with SentenceTransformers, indexed in Endee's HNSW vector database, and retrieved via cosine-similarity k-NN search to ground Groq's Llama 3.3 70B in a user-provided knowledge base with full source attribution.

FinSight AI

An AI-powered financial intelligence platform — parallel agents deliver probabilistic revenue forecasts, buy/sell signals, and peer benchmarks in under 20 seconds.