Technical Overview
Kobimusic provides Dettato, a 20M parameter audio-to-MIDI transcription model outperforming larger models like MuScriptor 1.3B. Built for music producers and developers, it features high efficiency and a training corpus free of copyrighted recordings, enabling commercial use. It operates under a credit-based freemium tier.
Analyst Evaluation: Pros and Limitations
Verified Advantages
- High parameter efficiency at only 20M parameters compared to heavier models.
- Trained without copyrighted material, ensuring safer commercial utilization.
- Open source model architecture suitable for self-hosted execution.
Technical Considerations
- Credit limits on the free tier restrict high-volume batch processing.
- Early stage ecosystem compared to long-standing transcription suites.
Technical Capabilities & Features
3/7ScorecardShow detailsHide details
Technical Scorecard: Kobimusic
Time to Value & Fit by Segment: Kobimusic
Near-instantaneous deployment with minimal technical friction.
Requires consulting technical documentation and basic credentials setup.
Fit Index by Organization Size
Pricing & TCOShow detailsHide details
Pricing
Model: FREEMIUM.
Available plans:
- Free$0/mo
Free Tier Verification:
- No credit card required
- Commercial use allowed
- Monthly recurring quota reset
- No mandatory watermarks
Billing Risks & Hidden Clauses: Kobimusic
Free credits covering approximately 30 pages of sheet music.
- Credit exhaustion requires waiting for renewal or upgrading plans for heavier batch workflows.
"free $0 credits a month, which is about 30 pages of sheet music"
Verified Quote: /research/dettato
Total Cost of Ownership (TCO) Projection: Kobimusic$0.00/moDeterministic cost estimation at 12 and 36 months based on team size, including SSO tax premiums and annual prepay discounts.Show detailsHide details
Usage Surcharges & Bill Shock Simulator: KobimusicWhat usage costs as you scaleDetect overage penalties before they impact engineering budget.Show detailsHide details
Procurement Strategy & Discounts: KobimusicB2B Negotiation PlaybookCorporate executive level with highest authority to approve budgetary exceptions.Show detailsHide details
Security & Data ExitShow detailsHide details
Compliance & Security Standards: Kobimusic
Data Liberation & Migration Runbook: KobimusicMIDI · JSONActionable escape runbook and credential export guarantees to mitigate vendor lock-in.Show detailsHide details
Deployment & Infrastructure Requirements: KobimusicApache-2.0Hardware specs and Docker directives to run on local servers, dedicated VPS, or Kubernetes without telemetry leak to the cloud.Show detailsHide details
Community & RepositoryShow detailsHide details
Technical Reputation of Kobimusic
Frequent Praises in Production
- High parameter efficiency at only 20M parameters compared to heavier models.
- Trained without copyrighted material, ensuring safer commercial utilization.
- Open source model architecture suitable for self-hosted execution.
Reported Production Frictions
- Credit limits on the free tier restrict high-volume batch processing.
- Early stage ecosystem compared to long-standing transcription suites.
Open source repository activity: Kobimusic11Stars, forks and release cadenceShow detailsHide details
Frequently Asked Technical Questions (Kobimusic)
What is Dettato and how does it work?
Dettato is an advanced audio-to-MIDI transcription model developed by Kobimusic that converts music recordings into digital sheet data using an optimized 20-million parameter neural architecture.
Can generated MIDI outputs be used commercially?
Yes, because the model was trained exclusively on recordings without copyright restrictions, the resulting outputs can be freely used for commercial purposes according to the public documentation.
What are the limits of the free tier?
The free tier grants regular monthly credits, which roughly translates to sheet music processing, making it well-suited for evaluations and moderate workloads.
Is the model open source?
Yes, the model is available as open source software, allowing technical users to run self-hosted deployments and integrate the weights into custom audio pipelines.