AI Voice Models
140+ royalty-free (2.0); multilingual
Languages
8: English, Chinese, Japanese, Korean, Spanish, Italian, French, Portuguese
Vocal Synth Engine
Verse25 (2.0 default) + legacy Verse24 support
Vocal Controls
Power, Soft, Breathy, Chest + Special Controls per voice
AI Instruments
Strings, Saxophones, Trumpet, Duduk + more
Generative AI Kits
Inspire Me, Music Enhancer, Add a Layer
AI Tools
Stem Splitter, Vocal to MIDI, Voice Changer, Doubles
DAW Integration
ACE Bridge 2 — VST / AU / AAX
Voice Cloning
Custom AI voice from uploaded vocal samples
Rendering
Cloud rendering + Local rendering
System Requirements
macOS 13+ · Windows 10+
File Formats
Import: MIDI, MusicXML, Audio · Export: Audio stems

What Is ACE Studio 2.0?

ACE Studio is an AI-driven music workstation developed by Timedomain (Beijing) in collaboration with Accidental AI. Its core function is AI vocal synthesis: you provide MIDI note data and lyrics, choose an AI voice model, and ACE Studio renders an expressive, human-sounding sung performance. The result behaves more like a recorded take than a static sample — with natural vowels, consonants, breaths, vibrato, and emotional nuance shaped by the AI engine.

Version 2.0 expands from a vocal synth into an all-in-one AI music studio environment, adding AI instruments, voice cloning, generative AI kits, and a more DAW-like Canvas workflow. For The Neon Dawn, ACE Studio serves as the AI vocal layer — likely a female voice — fed by MIDI from Cubase 15 Pro via the ACE Bridge plugin.

What's New in 2.0

FeatureDetails
Verse25 Engine NewNew vocal synth model replacing Verse24 as default. Adds Power, Soft, Breathy, Chest controls plus breath noise. Legacy Verse24 voices still accessible.
140+ Voice Models NewExpanded library including Rap, Pop, Chanson, Ballad, Kids Choir, Country. Multi-lingual voices across 8 languages.
AI Choir NewLayer multiple AI voices on a single track for choral/harmony arrangements.
Voice Blending NewBlend characteristics of two voices to create a unique hybrid AI voice.
AI Instruments NewViolin, viola, cello, saxophone (Bob Magnuson, Carlo Alfonso), trumpet (Xiaochuan Li), duduk. MIDI-driven expressive instrument rendering — not sample libraries.
Inspire Me NewGenerative AI kit: generate complete tracks from scratch or a description.
Music Enhancer NewGenerative AI kit: select Canvas content and reimagine it in a different style.
Add a Layer NewGenerative AI kit: add new instruments/vocals to an existing arrangement.
ACE Bridge 2 UpdatedImproved DAW integration — audio feeds directly into DAW timeline without exporting.
Canvas (DAW-like) UpdatedMore DAW-like track vs. timeline workflow within ACE Studio itself.
Doubles NewGenerate doubled/harmonized vocal parts automatically.
ACE Studio MCP Server NewAI control integration for advanced automation.

System Requirements

macOSWindows
Minimum OSmacOS 13 (Ventura)Windows 10
ACE Bridge formatsAU · VST · AAXVST · AAX

Interface Tour

The ACE Studio interface is organized around a central Canvas — the main timeline/arrangement area. Key areas:

AreaFunction
Toolbar (top)Voice Library icon (1st), Transport controls, Tool selection, Rendering controls
CanvasMain timeline: tracks run left-to-right. Click/drag to create clips. Each clip holds MIDI notes + lyrics for one phrase.
Track Panel (left)Per-track controls: Voice picture (click to change voice), Volume, Mute, Solo, AI Choir (+) button
Piano Roll (double-click clip)Opens note/lyric editor for that clip: edit pitches, timings, lyrics, phonemes, pitch curves, vocal controls
Parameter Lanes (below piano roll)Vocal Controls (Power, Soft, Breathy, Chest), Pitch deviation, Breath — drawn as automation envelopes
MixerPer-track volume, pan, effects

Voice Library

The Voice Library is ACE Studio's collection of AI voice models. Access it three ways:

Once open, drag a voice onto the Canvas to create a track, or click it and then click the Canvas to place it.

Voice Library Tabs

TabContents
All VoicesFull library of 140+ royalty-free AI voice models
My VoicesYour cloned voices (privately trained from your own recordings)
Shared With MePrivately shared cloned voices from other users
CommunityVoices cloned and published by the ACE Studio community; must be "collected" before use. If the creator removes a voice, 30-day grace period before access ends.
BlendedYour saved blended voices — stored to your account, accessible across devices.

Vocal Synth Models

The same AI voice can be available on multiple vocal synth model generations. Performance varies between generations — a Verse24 voice and a Verse25 version of the same voice may sound different.

ModelControls AvailableNotes
Verse25Power, Soft, Breathy, Chest + Special Controls (voice-specific)Default for 2.0. Most expressive control.
Verse24Emotion controls (legacy)Still accessible for pre-2.0 voices.

Creating AI Vocals — Core Workflow

  1. Open the Voice Library and drag an AI voice onto the Canvas to create a vocal track.
  2. Draw a clip on the Canvas by clicking and dragging on the track timeline.
  3. Double-click the clip to open the Piano Roll.
  4. Draw or import MIDI notes defining the melody pitches and durations.
  5. Enter lyrics — type directly onto notes, or paste full lyrics via the Lyrics Panel.
  6. Close the Piano Roll — ACE Studio renders the AI vocal performance for that clip.
  7. Open the clip again to refine: edit pitch, phonemes, vocal controls, or breath.
Quick Start Tip You can import a MIDI or MusicXML file directly (File → Import) to skip drawing notes by hand. ACE Studio places the MIDI into a clip ready for lyrics and voice assignment.

Editing Notes

In the Piano Roll, notes represent individual syllables. Standard tools: pencil (draw), pointer (select/move/resize), eraser. Notes can be split, merged, and resized. Note duration affects vowel length; very short notes may truncate consonants.

Editing Lyrics

Each note holds one syllable. Type a lyric directly on a selected note, then press Tab to advance to the next note. Pressing Space creates a rest/breath between words.

Lyrics Panel (paste full lyrics at once): open the Lyrics Panel, paste the entire lyric text, and ACE Studio distributes syllables across the existing notes. Review and correct any auto-split errors — especially with multi-syllable words.

Phoneme editing: Each lyric is automatically converted to phonemes (sounds). You can override individual phonemes if the AI mispronounces a word — useful for unusual names, slang, or poetic pronunciations. Refer to the Phoneme Dictionary in the Appendix for the phoneme set used per language.

Editing Pitch

The pitch editor shows the rendered pitch curve on top of your MIDI notes. The AI generates natural pitch deviations — vibrato, portamento, note transitions — automatically. You can:

Vocal Controls (Verse25)

Vocal Controls are the primary expression tool for Verse25 voices. They replace most of the older emotion controls. Each control can be automated as an envelope drawn in its parameter lane, or set globally with the track-level knob.

Basic Controls (all Verse25 voices)

ControlEffectUse For
PowerVocal strength and intensityDrive up for powerful choruses, dramatic moments, or an aggressive delivery. Pull back for intimate, close-mic verses.
SoftSoftness and gentleness of deliveryBreathy, quiet, or tender passages. Opposite end of the spectrum from Power.
BreathyBreathiness / air in the voiceAdds airy texture. Useful for whispered sections, sensual delivery, or indie/pop aesthetic.
ChestChest resonance and depth in lower rangeAdds warmth and fullness. Useful for grounded, full-bodied vocals. Great for lower-register lines.

Special Controls (voice-specific, Verse25+)

ControlEffectApplies To
RapEnhances clarity, speed, and rhythmic articulation. Higher = more aggressive, street-like delivery.Rap / hip-hop voices
OperaAdds classical bel canto technique: resonance, penetration, vibrato, dramatic tone.Opera / classical voices
Automation Tip Draw vocal control envelopes to change character through a phrase — e.g., start a verse with Soft high, then ramp Power up into the chorus. Right-click and drag over any envelope region to reset it to "Auto" mode. The Global Control Knob applies a constant offset on top of whatever envelope is drawn.

Breath

Breaths are inserted as dedicated note-like objects before vocal phrases. Add breath via the AI Parameters panel. Parameters: breath duration, breath volume. Breath is separate from the Breathy vocal control — Breath adds an audible inhale/exhale sound event; Breathy adds an airy quality to the singing itself.

Singing Languages

ACE Studio 2.0 supports 8 languages. Language is set per-track or per-clip:

LanguageNotes
EnglishBroadest voice selection; default for most use cases
Chinese (Mandarin)Largest voice model catalogue alongside English
JapaneseJ-Pop style voices well represented
KoreanAdded in 2.0
SpanishAdded in 2.0
ItalianAdded in 2.0
FrenchChanson style voices available
PortugueseAdded in 2.0

Not all voices support all languages. Check the voice card for supported languages. When using a language, ACE Studio uses the appropriate phoneme set for that language (see Phoneme Dictionary in Appendix).

AI Choir

AI Choir layers multiple AI voices on a single track for choral or harmony arrangements. Click the + button in the AI Choir section on the track panel to add voices to the choir. Each voice in the choir can use a different AI voice model. The choir renders all voices simultaneously from the same MIDI/lyric clip. Use Voice Blending within the choir for additional timbral control.

Voice Blending

Voice Blending creates a hybrid AI voice by interpolating between two voices. The result is saved as a custom blended voice under your account. Blended voices appear in the Blended tab of the Voice Library and are accessible across devices. Use blending to create unique timbres that don't exist in the stock library — e.g., blending a breathy indie voice with a powerful belter to get a controlled middle-ground character.

AI Instruments

AI Instruments generate expressive instrument performances from MIDI — without traditional sample libraries. The instrument models use deep learning to add natural articulation, dynamics, and performance nuance based on the MIDI input.

Available Instruments (2.0)

InstrumentArtist / Creator
ViolinVarious
ViolaVarious
CelloVarious
SaxophoneBob Magnuson, Carlo Alfonso
TrumpetXiaochuan Li
DudukVarious

Workflow is the same as AI Vocals: load an instrument from the Instrument Library onto a track, draw or import MIDI, and ACE Studio renders the performance. Expression parameters vary by instrument.

Arrangement in Canvas

The Canvas is ACE Studio's main timeline/arrangement view. It functions similarly to a DAW's arrangement window:

Transport

Standard DAW transport controls: Play, Stop, Record, loop region. BPM is set globally and applies to all tracks including arp/synth-style playback. ACE Studio can sync to external DAW transport via the ACE Bridge plugin.

Mixing

Basic per-track mixing within ACE Studio: Volume, Pan, Mute, Solo. For full mixing and effects, use the ACE Bridge to route audio into Cubase 15 Pro and mix there. ACE Studio's internal mixer is primarily for balance while composing.

File Management

OperationHow
Import MIDIFile → Import Files → select .mid or .musicxml. Notes populate a clip ready for voice/lyrics assignment.
Import AudioFile → Import Files → select audio file. Use for reference tracks, Vocal to MIDI processing, or stem splitting.
Export AudioFile → Export. Renders all tracks to audio stems. Choose individual tracks or a mixdown.
Project FilesACE Studio projects save all tracks, voices, MIDI, lyrics, and settings. Save regularly — cloud rendering requires an internet connection.

AI Rendering — Cloud vs. Local

Cloud RenderingLocal Rendering
RequiresInternet connection + ACE account creditsLocal install; no internet needed
SpeedFast; offloads to ACE serversDepends on local hardware
Voice availabilityAll voices including new releasesVoices must be downloaded locally first
Best forFinal renders, large projects, new voicesOffline work, privacy, speed on M-series Macs

AI Tools — Inspire Me

Generates a complete track from a text description or from scratch. Produces MIDI, vocals, and instruments on the Canvas. Good as a starting point or for quick demo generation. Results are fully editable after generation.

AI Tools — Add a Layer

Adds a new element (vocal, instrument, bass, drums, etc.) to an existing Canvas arrangement. Define a clip length if you only want a few bars. As of v2.0.5, Add a Layer references existing Canvas content when generating — so new layers are contextually appropriate to your current arrangement.

AI Tools — Music Enhancer

Select a region of your Canvas and Music Enhancer "reimagines" it in a different musical style. Useful for arrangement experiments — try your verse in a different genre or texture without committing.

AI Tools — Voice Changer

Transforms an input vocal recording to sound like a selected AI voice. Useful for: quickly auditioning how a melody sounds in a different voice before committing to full synthesis, converting scratch vocals to a polished AI performance style, or applying a cloned voice to existing recordings.

AI Tools — Stem Splitter

Takes a mixed audio file and separates it into stems — vocals, instruments, etc. Useful for:

Load the file → click Split → choose stem type to extract → export. Quality is best on clean, non-effects-heavy recordings.

AI Tools — Vocal to MIDI

Analyzes an audio vocal recording and extracts pitch and lyrical content, generating a MIDI clip that can be used directly for AI vocal synthesis. Workflow:

  1. Import the audio vocal (spoken or sung) into ACE Studio.
  2. Apply Vocal to MIDI — ACE extracts pitch data and lyric content from the audio.
  3. Review and correct the generated MIDI notes and lyrics (some editing expected, especially for fast passages).
  4. Assign an AI voice to the track and render using the corrected MIDI.
Best Results Use clean, dry recordings without reverb, delay, or heavy harmonies. Even if you're not a confident singer, humming or speaking a melody into a mic gives Vocal to MIDI a clear reference to work from.

AI Tools — Doubles

Generates doubled or harmonized vocal parts from an existing AI vocal track. Adds the thickened double-tracking effect typical of professional vocal production. The doubled voice uses a slightly varied performance to sound natural rather than a simple copy.

Voice Cloning

Voice Cloning trains a custom AI voice model from your own vocal recordings. The resulting cloned voice can then sing any melody with any lyrics — including entirely new songs.

For Vocal Synth cloning: upload vocal samples → ACE trains the model → cloned voice appears in My Voices tab → use it like any other AI voice on vocal synth tracks.

For Voice Changer cloning: separate clone trained specifically for the Voice Changer tool — transforms audio recordings to sound like you.

Privacy Note Cloned voices are stored privately under your account by default. You can optionally publish them to the Community tab. If you publish and later take a voice down, other users who collected it have a 30-day grace period before access ends.

DAW Integration — ACE Bridge 2

ACE Bridge 2 is a plugin (VST / AU / AAX) that creates a live connection between ACE Studio and your DAW. Audio from ACE Studio feeds directly into the DAW's timeline without manual exporting or bouncing.

FormatDAW Compatibility
VSTCubase 15 Pro, most Windows/Mac DAWs
AULogic Pro, GarageBand, macOS DAWs
AAXPro Tools

Setting Up ACE Bridge with Cubase 15 Pro

  1. Download ACE Bridge 2 from acestudio.ai and install. Cubase will detect it on next launch.
  2. In Cubase: create a new Instrument Track and load ACE Bridge 2 as the instrument.
  3. Open ACE Studio (standalone). Both applications are now linked via the Bridge.
  4. Build your vocal/instrument arrangement in ACE Studio's Canvas.
  5. ACE Studio audio feeds into the Cubase Instrument Track in real-time. Record-enable the track to capture it to audio in Cubase.
  6. Use Cubase's transport to control playback — ACE Studio syncs to Cubase's BPM and position.
Workflow Tip for The Neon Dawn Build your synth arrangement in Cubase first, then open ACE Studio alongside it via Bridge. Use Vocal to MIDI on a scratch vocal or hummed reference to quickly generate a MIDI melody, then refine and assign an AI voice. Automate Vocal Controls (Power/Soft/Breathy) to match the energy of each section of the song.

Keyboard Shortcuts

ActionShortcut
Play / StopSpace
New projectCmd/Ctrl + N
Save projectCmd/Ctrl + S
Import filesCmd/Ctrl + I
UndoCmd/Ctrl + Z
RedoCmd/Ctrl + Shift + Z
Open Voice LibraryClick Toolbar icon 1
Draw note (Piano Roll)Pencil tool selected + click/drag
Delete noteRight-click note, or select + Delete/Backspace
Advance to next lyric noteTab (while typing lyrics)
Insert rest/space (lyrics)Space bar
Erase pitch envelope regionRight-click + drag over region
Zoom in (Piano Roll)Cmd/Ctrl + scroll wheel
Select allCmd/Ctrl + A

Full shortcut list: docs.acestudio.ai/appendix/shortcuts

Creative Library

SectionContents
SamplesRoyalty-free audio samples for use in projects or with Add a Layer
Song TemplatesPre-built project templates to start from — useful for exploring ACE Studio's workflow quickly
================================================================================
Source: ACE Studio Official Documentation (docs.acestudio.ai)