Quick Start Guide
Sibelius Edition
Cantai renders expressive vocal performances directly from your Sibelius score. No manual phoneme editing, no fiddling with MIDI — just write your music and hear it sung.
What Cantai Does
Cantai reads your score — notes, lyrics, dynamics, tempo, expression markings — and generates a realistic sung vocal performance. It works inside Sibelius as a playback device, so your vocal parts play back through Cantai automatically alongside the rest of your ensemble.
System Requirements
macOS
- macOS 14 Sonoma or later
- Apple Silicon (M1 or later)
Windows
- Windows 10 (2020 update) or later
- x86-64 processor
Installation & Activation
- Create a free account at cantai.app (or log in if you already have one).
- Go to Downloads and download the installer for your OS, then run it.
- Launch Sibelius — Cantai will appear as an available playback device.
- Open your Profile page to find your Account Token.
- Activate by pasting your Account Token from your Profile into the Cantai interface and clicking Activate.
Setting Up a Vocal Part
1. Add lyrics to your score
Select the first note in your vocal part and press Cmd+L (macOS) or Ctrl+L (Windows) to begin entering lyrics. Type your lyrics, pressing Space to advance after a complete word, or - (hyphen) to advance after each syllable of a multi-syllable word.
2. Load & activate Cantai in Playback Devices
Open Play > Setup > Playback Devices. In the Active Devices tab, find Cantai in the Available devices column, select it, and click Activate >> to move it into the Active devices list. Add one Cantai instance per vocal staff you want Cantai to sing — each can sit alongside other devices such as NotePerformer.
3. Assign each instance to a staff in the Mixer
Open the Mixer (M). On each vocal staff's strip, open the input-device dropdown and select the Cantai instance you want that staff to play through.
4. Choose a voice
On the staff's Cantai strip in the Mixer, open the program dropdown and follow CantAI → Voice, then pick a category — Female, Male, or Ensemble — and choose the singer. The Ensemble category contains the choral voices (choir female and choir male).
5. Press Play
That's it. Whenever you change anything that affects a vocal part — notes, lyrics, dynamics, tempo, or expression — Cantai automatically re-renders just the affected segments. No manual refresh needed.
Cantai Settings
You only need the Cantai interface for occasional adjustments — changing the number of choral voices, resetting an instance, clearing the cache, or reporting a bug. To open it, click the gear icon on the staff's strip in the Mixer. The interface shows the active voice and the detected part (e.g. Soprano).
Open the menu in the top-right to adjust instance settings: choir section count (3–10 voices per part for choral voices), Clear Cache, Reset Instance Settings, and Diagnostic logs export.
Choral Voices
Cantai includes two dedicated choir voices — Choir — Female and Choir — Male — which render a full choral section rather than a single singer. To set the number of voices per part (3–10), open the menu in the Cantai interface and adjust the choir section count.
The menu also provides Clear Cache and Reset Instance Settings options if you need to troubleshoot or start fresh.
Supported Languages
Cantai currently supports English and Latin, with more languages coming in subsequent updates.
Language is detected automatically from your lyrics. For best results, ensure your lyrics are spelled correctly — Cantai's phoneme engine derives pronunciation directly from the text.
Dynamics and Expression
You do not need to draw in any MIDI automation. Write your score the way you would for human performers, and Cantai interprets it.
Dynamic markings p, mp, mf, f, ff, etc. Hairpins crescendo, decrescendo Tempo markings Allegro, Andante, ritardando, etc.
Tips for Best Results
- after each syllable to advance to the next note.
Exporting Audio
- Choose File > Export > Audio
- Select the output folder and the staves you want to include
- Choose your format — WAV for highest quality, MP3 for smaller file size
- Click Export
Cantai audio exports at full quality — the same engine used for real-time playback renders the final file.
Known Issues
If a voice isn't rendering, or its slot shows a cross (×) instead of the singer's photo in the Cantai window, open the affected Cantai interface and change the voice again from the Sibelius mixer. The voice will then load and render normally. We're working to fix this as soon as possible.
Reporting Issues
If something isn't working, reach us through the Help chat button in the bottom-right corner of any page on cantai.app. Please include your diagnostic logs so we can investigate.
To generate them, open the menu in the Cantai interface and, under Support, click Export logs…
Cantai saves a single timestamped zip archive (e.g. cantai-logs-2026-06-04-085622.zip). Drag that file into the Help chat window.
Licensing
Cantai for Sibelius requires a lifetime license — unlimited installs, free updates.
View pricing and get your license →Cantai is made by Turing Opera Workshop. We build tools for composers who take vocal writing seriously.