# introlab/odas

ODAS: Open embeddeD Audition System

Repository: https://github.com/introlab/odas
Canonical: https://ross.abutalabs.com/products/odas
Language: C
License: MIT
License Family: permissive
Topics: sound, separation, localization, tracking, beamformer, real-time, embedded, audition, robotics
Last push: 2024-12-05T14:52:10+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3348, "days_push": 636, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1048, forks 281 (observed 2026-08-28T04:03:22.503549+00:00)

## What it is
ODAS (Open embeddeD Audition System) is a C library for real-time sound source localization, tracking, separation, and post-filtering using microphone arrays. It is optimized to run on low-cost embedded hardware and is commonly used in robotics audition applications.

## Use cases
- localize sound sources with a microphone array in real time
- track moving speakers with embedded hardware
- separate and post-filter audio from multiple sound sources
- build a robot that can hear and locate sounds
- process microphone array audio on low-cost embedded boards
- integrate sound source localization into a ROS robotics project

## When to choose
- you need real-time sound source localization, tracking, or separation in C
- you are targeting embedded or low-cost hardware like Raspberry Pi
- you work with microphone arrays and robotics audition
- you want an MIT-licensed, well-documented audio audition library with a companion GUI and ROS integration

## When to avoid
- you need high-level speech recognition or transcription rather than localization and separation
- you prefer a Python or managed-language library rather than C
- you need offline batch audio processing rather than real-time streaming
- you require Windows-first tooling without building from source

## Facets
- artifact type: library
- maturity: stable
- function: audio-processing, speech-recognition, machine-learning
- domain: robotics, embedded-systems, speech-processing
- platform: embedded, cross-platform, cpp
- tags: sound-source-localization, sound-source-separation, beamforming, microphone-array, real-time-audio, audition, tracking, audio, linux

## Member repositories
- introlab/odas (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:22.503549+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:00:44.389494+00:00, confidence not recorded.
  - readme: https://github.com/introlab/odas (fetched 2026-08-28T04:03:22.503549+00:00, sha 0fefb31637b2)
- Data as of 2026-08-30T08:39:29.467469+00:00.