Scoring Notes

Q & A(I)

Scoring Notes

Show Notes

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

Tomplay Smart Page Turn Smartleggio Piascore SampleSumo Music Following Antescofo (IRCAM)

MCP bridges (community projects)

mcp-musescore dorico-mcp-server (also on PyPI)

Music generation

Suno

NYC Music Services / Notation Central

PDF Batch Utilities

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 a

More from Scoring Notes

Oct 3, 2026

Opening someone else’s notation file can take a little detective work. So can opening your own file from a year ago. After two 90-minute Q&A episodes, Philip Rothman and David MacDonald return for a (slightly) shorter conversation about figuring out what’s going on in a score before you start changing it. David brings questions from helping his students; Philip brings his experience exchanging files with composers, clients, and colleagues. We start with the messages that appear when a file opens. There may be something useful in that dialog you just dismissed! Missing fonts, in particular, deserve a look before “OK fatigue” takes over. Once the file is open, what are you actually looking at? A concert-pitch score or a transposed one? Where did that instrument go? We talk about making hidden information visible in Sibelius and Dorico, and checking whether a setting applies to one item, one part, or much more than you intended. Text styles, wildcards, and tokens get some attention, as do the various ways of showing the same music in different scores, parts, and layouts. David describes a “fragile file”: change one thing, and something elsewhere breaks. That prompts a discussion of when to use the software’s more sophisticated features and when a simpler setup might be easier for a collaborator to manage. We also look at what to include when sending a file, from comments explaining an unusual choice to a reference PDF showing how it’s supposed to look, and the proofreading checks that can help before it goes out the door. There’s plenty here for students — but we’re all students here. Have you solved a notation problem whose cause surprised you? Tell us in the comments, or at [email protected]. It may make it up the pneumatic tubes from the mailroom to the C-suite.

Sep 5, 2026

You sent more questions than one episode could hold, so we split them in two. Part one was brought to you by two letters: AI. This is everything else in the mailbag, from the practical side of the music notation software and technology world. Philip Rothman and David MacDonald work through the rest of the mailbag: an iPad that won’t behave like a desktop, an app that has gone quiet, a singing plug-in that is rapidly evolving, world instruments that have to be taught to a notation program, a page somebody has to read at tempo, organizing a lifetime of files, keeping current with operating systems, and — perhaps the most practical question of all — our take in response to a question from a young copyist asking how any of this becomes a living. The answers range over layout options and staff sizes, expression maps and subscription libraries, file metadata and backup schemes, security updates and Apple silicon, and a set of accessibility guidelines deserving of wider recognition. Believe it or not, there are a few things here we plainly don’t know. Underneath most of it is the same instinct: keep the things you control in good order, and keep an exit from the things you don’t. Export the files. Learn the search box. Test the backup. Ask the player what size they can actually read. And never underestimate the value of a performance librarian in your corner. Thanks to everyone who wrote in. We take questions and suggestions year-round at [email protected].

Jul 4, 2026

Philip Rothman and David MacDonald are back after a short break, and true to form, the conversation drifts from yard work and heat waves before landing on the actual business at hand: it’s time to open the phone lines again. For the third time — after 2023’s three-part marathon and last year’s round — Scoring Notes wants to hear directly from you, on any topic in the world of music notation software and related technology, or anywhere adjacent to it. Send your question as an email to [email protected], or record it as a voice memo and send it as an email attachment or file-sharing link, or drop it directly here. However you send it, questions are due by Wednesday, July 22, 2026, and the best of them will form the basis of the next episode. To get your wheels turning, the rest of the episode is a quick lay of the land for the first half of 2026. Dorico 6.1 and 6.2 brought a wave of guitar refinements and paragraph-level smart quotes, and picked up support for the Cantai vocal synthesis plug-in along the way. Sibelius matched that pace across three releases, capped by 2026.6‘s long-overdue fix for cross-staff accidentals, plus VST3 support and a restored dark theme. MuseScore Studio 4.7 rounded out its 4.x line with a much-improved ‘R’ for repeat, new parenthesis and bracket options, and its own Cantai support. For the full list of what shipped, plus lots more from Scoring Notes’ coverage of the first six months of the year, see our mid-year summer summary. Cantai itself has moved fast since Richard deCosta joined the podcast in May: it now runs across Dorico, Sibelius, and MuseScore Studio, and pricing has come down substantially to a unified $9.99/month or $149 lifetime license, with new “Ottetto” choir ensembles added along the way. Full details are in our Cantai 3.0.0 coverage. Finally, Philip previews news he’s especially excited about: the 2027 MOLA Conference heads to San Francisco, April 30 – May 3, with a reimagined Tech Fair that he’ll be producing and programming himself, built around a single throughline — the life cycle of a score. He’s inviting participation from anyone working in music technology, notation, publishing, or archiving, and floats the idea of adjacent meetups for groups like the W3C Music Notation Community Group, the MEI community, and the MIDI Association. Full details are in our MOLA 2027 announcement. Meanwhile, get those questions in by July 22, and enjoy the rest of your summer.

Jun 6, 2026

Six years after our “Score preparation and production notes” episode — Episode No. 2 — essentially launched the podcast, 163 episodes later, Philip Rothman and David MacDonald return to the article that inspired the conversation: David’s score preparation checklist. The principles — respect for performers, readable parts, enough time for page turns — are as true as ever. But almost every specific tool reference in the original has a fuller story now. The conversation moves section by section, serving as a reminder of the timeless principles and exploring all of the meaningful changes in the technology. Dorico’s live-reference cue system has become the standard no one else has matched — and the ease of it has quietly changed how generously cues get applied. The Dorico 6 Proofreading panel represents a new category of preparation tool, while the Sibelius plugin ecosystem has its own parallel answers. The condensing and decondensing workflows now available in both Dorico and Sibelius 2025.2 have transformed what was once among the most tedious jobs in parts preparation, and Sibelius 2025.7’s Auto-Respace toggle closes a gap that used to just be accepted. Two sections are entirely new to the checklist: digital delivery — where the iPad has become as common in rehearsal as a music stand — and a pointed look at the file-organization habits that make or break a delivery package. This one’s chock-full of tips, resources and advice — with David’s updated accompanying article to come soon.

May 2, 2026

What if your notation software could sing? At the top of this episode, we play a short clip, performed entirely in Dorico with NotePerformer handling the orchestra, and a plugin called Cantai rendering the baritone voice. That voice is synthesized directly from the Dorico score with minimal configuration, and it marks the arrival of something the notation world has been waiting for for a long time. Philip Rothman and David MacDonald talk with Richard deCosta, composer, software developer, and founder of Cantai and the Turing Opera Workshop, about what it took to build it. The conversation goes deep on the technology: why synthesizing the voice is fundamentally harder than synthesizing instruments, how the phonemizer works, why Cantai renders offline rather than in real time, and what it really means to build a plugin that reads a score rather than simply receiving MIDI. Richard also explains how years of frustration with the disconnect between notation and external vocal synthesis tools — from EWQL Symphonic Choirs and WordBuilder to ACE Studio and Synthesizer V — led to the central insight behind Cantai: that the lyrics were always there in the score; they just weren’t being passed to the playback engine. We also dig into the ethical and business model Richard has built around the singers whose voices power Cantai. Every vocalist is contracted, paid a competitive recording fee, and receives an ongoing share of the product’s profits in proportion to how much their voice is used. Cantai is already live for MuseScore Studio and Dorico, and arriving for Sibelius on May 30. The roadmap — more languages, less vibrato, Broadway and jazz styles, and a thought-provoking vision for the future of real-time vocal generation — gives us plenty to look forward to.

See all episodes →