Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2512.03289 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917121268645888 |
|---|---|
| author | Elkins, Aaron C Singh, Sanchit Kieback, Adrian Blankenship, Sawyer Amadasun, Uyiosa Philip Chadha, Aman |
| author_facet | Elkins, Aaron C Singh, Sanchit Kieback, Adrian Blankenship, Sawyer Amadasun, Uyiosa Philip Chadha, Aman |
| contents | Digital Audio Workstations (DAWs) offer fine control, but mapping high-level intent (e.g., "warm the vocals") to low-level edits breaks creative flow. Existing artificial intelligence (AI) music generators are typically one-shot, limiting opportunities for iterative development and human contribution. We present DAWZY, an open-source assistant that turns natural-language (text/voice/hum) requests into reversible actions in REAPER. DAWZY keeps the DAW as the creative hub with a minimal GUI and voice-first interface. DAWZY uses LLM-based code generation as a novel way to significantly reduce the time users spend familiarizing themselves with large interfaces, replacing hundreds of buttons and drop-downs with a chat box. DAWZY also uses three Model Context Protocol tools for live state queries, parameter adjustment, and AI beat generation. It maintains grounding by refreshing state before mutation and ensures safety and reversibility with atomic scripts and undo. In evaluations, DAWZY performed reliably on common production tasks and was rated positively by users across Usability, Control, Learning, Collaboration, and Enjoyment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_03289 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DAWZY: A New Addition to AI powered "Human in the Loop" Music Co-creation Elkins, Aaron C Singh, Sanchit Kieback, Adrian Blankenship, Sawyer Amadasun, Uyiosa Philip Chadha, Aman Human-Computer Interaction Digital Audio Workstations (DAWs) offer fine control, but mapping high-level intent (e.g., "warm the vocals") to low-level edits breaks creative flow. Existing artificial intelligence (AI) music generators are typically one-shot, limiting opportunities for iterative development and human contribution. We present DAWZY, an open-source assistant that turns natural-language (text/voice/hum) requests into reversible actions in REAPER. DAWZY keeps the DAW as the creative hub with a minimal GUI and voice-first interface. DAWZY uses LLM-based code generation as a novel way to significantly reduce the time users spend familiarizing themselves with large interfaces, replacing hundreds of buttons and drop-downs with a chat box. DAWZY also uses three Model Context Protocol tools for live state queries, parameter adjustment, and AI beat generation. It maintains grounding by refreshing state before mutation and ensures safety and reversibility with atomic scripts and undo. In evaluations, DAWZY performed reliably on common production tasks and was rated positively by users across Usability, Control, Learning, Collaboration, and Enjoyment. |
| title | DAWZY: A New Addition to AI powered "Human in the Loop" Music Co-creation |
| topic | Human-Computer Interaction |
| url | https://arxiv.org/abs/2512.03289 |