We asked for your questions, and you sent so many that one episode couldn’t hold them. This is part one of two — and part one is brought to you by two letters: A and I. That wasn’t the plan; it’s just where the mailbag pointed.
Philip Rothman and David MacDonald take on the growing expectation that artificial intelligence should be able to turn a scan, recording, or generated track into finished, usable sheet music. Why is that still so difficult? And where can AI genuinely help musicians and music preparation professionals today?
The discussion ranges from optical music recognition and audio transcription to proofreading, house styles, sample libraries, score following, and the potential for language models to communicate directly with notation software. Along the way, Philip proposes the “Gould test” as the music preparation equivalent of the Turing test.
Underneath it all are larger questions about the value of expertise, the role of human judgment, and where responsibility lies when the technology gets it wrong.
The rest of the mailbag — the questions that have nothing to do with AI — is coming next month.
Products mentioned
Notation software
- Dorico (Steinberg)
- Sibelius (Avid)
- MuseScore Studio (Muse Group)
- Flat (Tutteo)
- StaffPad
Scanning and optical music recognition
- NoteVision (Muse Group)
- Soundslice sheet music scanner
- Newzik
- PlayScore 2
- SmartScore 64 Pro (Musitek)
- Opuscan (Tutteo)
- Audiveris (open source)
Audio transcription
- Klang.io and Transcription Studio
- Songscription
- Basic Pitch (Spotify) (open source)
- Magenta MT3 (Google) (research)
Playback and vocal synthesis
- NotePerformer (Wallander Instruments)
- Cantai (Turing Opera Workshop)
AI arranging and orchestration
- ArrangementLabs
- NotationAI
- ScoreSynth
- Orchidea (IRCAM / HEM / UC Berkeley)
Score following and page turning
MCP bridges (community projects)
- mcp-musescore
- dorico-mcp-server (also on PyPI)
Music generation
NYC Music Services / Notation Central
Other tools mentioned
- Name Mangler / Renamer
- Claude (Anthropic)
Previous Scoring Notes posts and podcast episodes
Directly mentioned or closely related:
- Half-time report: what’s new, and a call for your questions (previous episode — the call for these questions)
- You have questions, we have answers (2025 listener questions episode)
- Asked and answered, part 1 (2023, the first listener-questions episode)
- Scanning the current OMR landscape (Steve Morell’s six-product comparison, December 2024)
- A snapshot of music scanning apps — and picturing the future (companion podcast)
- Dorico and The Rite of Spring (Stephen Taylor, January 2021)
- The “rite” way to copy old scores into new software (podcast with Stephen Taylor, February 2021)
- NAMM 2026: Sounding out the inputs with Klang.io’s Sebastian Murgul and the companion podcast
- NAMM 2026: An Avid Sibelius discussion with Sam Butler and Joe Plazak and the companion podcast
- NAMM 2026: Piascore’s bet on interactivity
- Marie Chupeau and the human side of Newzik’s artificial intelligence (podcast, November 2021)
- From zero to slice: Soundslice takes on optical music recognition with AI (podcast with Adrian Holovaty, December 2022)
- Dorico 6: Proof positive (review — the Proofreading panel)
- Dorico 6.0.22 extends proofreading capabilities (the “ignore issue type” feature)
- Behind “Behind Bars” with Elaine Gould (podcast, July 2023)
- Cantai now sings straight from Dorico (review)
- Richard deCosta gives your score a voice (podcast, May 2026)
- NotePerformer reverses course (the removal of third-party Playback Engines)
- NotePerformer updated to 5.1.0
- Comma sense: Command Search in Sibelius
- NAMM 2025: Imbibing and transcribing with Oriol López Calle and the companion podcast (AI-assisted transcription inside a professional service)
- PDF Batch Utilities get a major rebuild — and a brand new app
- The rights stuff (podcast — rights and permissions)
Other references
- Carlos Peñarrubia et al., “MuSViT: A Foundation Vision Model for Sheet Music Representation” — Pattern Recognition and Artificial Intelligence Group, University of Alicante; posted June 30, 2026, accepted at ECCV 2026. Project page
- Christopher W. White, The AI Music Problem: Why Machine Learning Conflicts With Musical Creativity (Routledge, 2025)
- Elaine Gould, Behind Bars: The Definitive Guide to Music Notation (Faber Music)
- NotePerformer: Playback Engines discontinued — Arne Wallander’s own explanation
- “Detecting Notational Errors in Digital Music Scores” — research on automated score checking
- Musicians’ Union arranging, music preparation and orchestration rates (UK)
- Copyright and Artificial Intelligence, Part 2: Copyrightability — U.S. Copyright Office report
Timely subject. I recently started covering it (the intersection between classical music and AI) on my Substack, Augmented Fifth, where I track the musical capabilities of AI and evaluate new models (primarily LLMs) as they become available.
Personally, I expect AI to have a big impact on engraving. When I asked various LLMs to upscale scans of old sheet music, the results were stunningly beautiful — for an engraver like me, it was like seeing Michaelangelo’s fully restored frescoes in the Sistine Chapel. But the results were also imperfect. You would have to put a lot of effort into fixing them before they became usable.
Still, what’s possible today is much better than what was possible two years ago. I can only imagine what will be possible in another two years. I’m genuinely excited to find out.