This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
AvianEcho is an offline-capable, Edge AI bird identification dashboard designed to run entirely on local hardware. The application captures real-time environmental audio or processes uploaded sound files, standardizes the audio frequencies, and classifies the exact bird species using an optimized ONNX BirdNET model.
To create a complete field guide experience, it dynamically fetches verified wildlife photography from the Wikipedia REST API, generates fascinating context and lore using a locally hosted Gemma LLM, and reads those facts aloud using the Piper text-to-speech engine.
Demo
Code
🐦 AvianEcho — Real-Time Edge AI Bird Guide
Listen to Nature. Discover the Birds Around You.
An AI-powered bird identification and discovery platform combining real-time audio analysis, edge machine learning, local language models, and voice-based storytelling
🧭 Explore AvianEcho
📖 About the Project
AvianEcho is an AI-powered bird identification and exploration application that helps users discover bird species through their vocalizations.
Bird calls are one of nature's most useful identification signals, but recognizing them can be challenging without specialized knowledge. AvianEcho makes this process more accessible by combining audio classification, locally running AI models, educational content generation, and natural-sounding voice feedback.
The application analyzes live microphone input or uploaded audio recordings, identifies likely bird species through a BirdNET-based classification pipeline, and presents the results through an interactive Streamlit dashboard.
It can also generate engaging bird facts using a locally hosted Gemma 2B language model and read those facts aloud using…
How I Built It
I built the frontend using Streamlit to create a clean, dual-tab interface for both file uploads and live microphone scanning. The core backend relies on Python, utilizing librosa and numpy to manipulate audio chunks into the exact 48kHz, 3-second mono format required by the classification model.
To keep this a true Edge AI prototype that can run offline in the wilderness, I avoided cloud APIs for the heavy lifting. I implemented llama-cpp-python to run a local Gemma 2B model for generating educational bird facts, and piped that text into a standalone Piper TTS Windows executable for instant voice synthesis. The only external call is to the Wikipedia REST API to ensure the photographs displayed are biologically accurate rather than AI-generated hallucinations.
Why Does Open Innovation Matter?
Open innovation democratizes access to advanced technology. By leveraging open-source models, lightweight TTS engines, and open knowledge bases like Wikipedia, a student can build a sophisticated environmental monitoring tool without requiring massive cloud computing budgets or proprietary APIs. In the context of wildlife conservation, open innovation ensures that tools like AvianEcho can be freely modified, deployed on low-cost hardware like Raspberry Pis, and utilized in remote habitats where internet access doesn't exist.
Prize Categories
Best use of Gemma
Top comments (0)