Back to News
Kyutai and Mirelo•July 10, 2026
MuScriptor
Open Source
Music Transcription
Audio-to-MIDI
Generative AI
Open Science
### TL;DR
MuScriptor is an open-weight, multi-instrument music transcription model that converts complex, multi-instrument audio recordings into symbolic MIDI representations. Developed by Kyutai and Mirelo, the model leverages a decoder-only Transformer architecture trained on a large-scale dataset of 170,000 real-world songs across diverse genres.
Key Insights & Metrics
Pricing
Free
Cost structure
Version
0.2.1
Current release version
Hardware
Small variant is suitable for CPU-only machines; large variant is optimized for GPU acceleration
Compute requirements
Category
Open Source
Licensing model
Region
France
Primary region
Key Features
- Multi-instrument transcription from full audio mixes
- Instrument conditioning to selectively transcribe specific instruments
- Three-stage training pipeline (synthetic pre-training, real-world fine-tuning, and reinforcement learning)
- Three scalable model variants: small (103M), medium (307M), and large (1.4B)
- Includes CLI and FastAPI-based web UI for real-time live piano roll visualization
- Outputs standard MIDI files for compatibility with DAWs and music analysis software
Discussion
0
Upvotes
0
Downvotes
0 reviews
Sign in to leave a review
Reviews
No reviews yet. Be the first to review!