---
title: CODA
emoji: 🎵
colorFrom: yellow
colorTo: orange
sdk: gradio
sdk_version: 6.16.0
python_version: '3.12'
app_file: app.py
pinned: false
license: mit
short_description: Finish what you started. A local AI that continues your songs.
---

# CODA

You have an unfinished song. Maybe you ran out of ideas at the bridge, maybe the groove just stops at 0:47. Upload it. CODA listens, figures out what key you're in and where the beat lands, then continues the music from where you stopped. Vocals, instruments, lyrics -- it picks up all of it.

Everything runs locally. No audio leaves your machine, no cloud APIs, no subscriptions. The whole stack fits under 13B parameters: MusicGen Large handles the music continuation, Whisper + Demucs pull and transcribe vocals, Qwen3 writes new lyrics that match your style, and librosa does the key/tempo detection without any ML at all.

Upload a WAV, MP3, or FLAC (under 60 seconds). You'll see the detected key, tempo, and duration right away. Hit continue and CODA generates what comes next.

---

Built by Tony Winslow for the Build Small Hackathon 2025. MIT license.