| Model Name | Description | Language Support |
|---|---|---|
| Advanced vocal synth model with high performance and quality. | English, Spanish, Italian, French, Portuguese, Korean, Chinese, Japanese | |
| Verse24 | A vocal synth model enhanced with English and Spanish capabilities. | English, Spanish, Chinese, Japanese |
| Solo24 | A vocal synth model expanded from Verse24, designed for voice cloning. | English, Chinese, Japanese |
| Verse23B | Enhanced based on the Verse23 model. | English, Chinese, Japanese |
| Solo_D | A vocal synth model expanded from Verse23, designed for voice cloning. | English, Chinese, Japanese |
| Solo23 | A vocal synth model expanded from Verse23, designed for voice cloning. | English, Chinese, Japanese |
| Verse23 | ACE Studio's first multilingual vocal synth model. | English, Chinese, Japanese |
| Editing Notes | /pages/sUQxepGdFR6n6XLdl3Na | /files/GGImoEO5yQgYCQhTaeDK |
| Editing Lyrics | /pages/bqqgOS0VxizQT36mpTqO | /files/XJZvs0Rn1WuRJtI1pCgU |
| Editing Pitch | /pages/ZWJW2qSPQflkwF8CDDtB | /files/EIDSxvnluG15zw14cUfU |
| Vocal Controls | /pages/g8JEOeCc66qrIyhLHnpY | /files/1TGzRCHGanKOnKilrznC |
| Singing Languages | /pages/NXzyWoV1u7gwjCqs5jCi | /files/cBUJdPbj6hGaFqB0kU6d |
| Unison Mode | /pages/Y9uyG92Y19XxpxN0q1OX | /files/4fBHnbl6r41g0H94ykCk |
Can I import MIDI or MusicXML files?
Yes. You can import your MIDI or MusicXML files into ACE Studio. For more information, please refer to [Import Files](/project/file-management/import-files).Can I paste the whole lyrics from elsewhere?
Yes. You can paste the entire lyrics into your melody using the [Lyrics Panel](/ai-vocal-synth/creating-ai-vocals/editing-lyrics#edit-with-lyrics-panel).Can I add a breath before a phrase?
Yes. You can add breath in the AI parameters panel. For more information, please refer to [Breath](/ai-vocal-synth/creating-ai-vocals/breath).Power
“Power” controls the strength and intensity of the vocal delivery. Increasing this parameter gives the voice more energy and impact, ideal for powerful choruses or dramatic moments.Soft
“Soft” adjusts the overall gentleness and smoothness of the voice. Higher softness makes the voice sound more delicate and soothing, suitable for ballads or intimate moments.Breathy
“Breathy” controls the amount of airiness or breath-like quality in the voice. Increasing this parameter adds a whispery, ethereal texture, perfect for dreamy or emotional passages.Chest
“Chest” enhances the resonance and depth in the lower vocal range, giving the voice a fuller and more grounded tone. This is useful for creating a warm and rich vocal presence.Rap
"Rap" controls the rap style of the voice. Increasing this parameter enhances the clarity, speed, and rhythm of the articulation, making the voice more aggressive and street-like. It is suitable for rap sections in hip-hop music, pop songs, or any passages requiring strong rhythmic expression.Opera
"Opera" injects classical bel canto singing techniques into the voice. Increasing this parameter enhances the resonance and penetration of the voice, adds brilliant vibrato and dramatic tone, making the voice sound more bright and full. It is ideal for singing classical arias, brilliant segments in musicals, or adding a grand, epic feeling to songs.Chinese Opera
"Chinese Opera" adds the unique charm and singing style of traditional Chinese opera to the voice. Increasing this parameter makes the articulation more distinctive, the tone brighter and higher-pitched, and incorporates the common melismatic and ornamental sounds of Chinese opera. It is suitable for singing opera excerpts or integrating "Chinese style" elements into modern music.Air
This is to control the airiness of the vocal. You can make the vocal more raspy or bright by increasing this parameter. * You can slightly increase air when it comes to the powerful part. * We recommend just making a slight change on this, extreme values might result in unexpected performance.Falsetto
This is to control the amount of falsetto of the vocal. * When the key is low, increasing the falsetto might not bring much falsetto as expected. * If you want more falsetto, we recommend decreasing tension at the same time for a better result. * We recommend just making a slight change on this, extreme values might result in unexpected performance.Tension
This is to control the softness of the vocal. * Lower this value, the vocal will be softer. Increase this value, the vocal will be tight. * We recommend just making a slight change on this, extreme values might result in unexpected performance.Energy
This is to control the power of the vocal. * This parameter is not just volume of the sound. * If you want a gentle sound, we recommend decreasing tension at the same time.# Breath Add and adjust breaths in ACE Studio to make vocal performances sound more natural.
| Cover image | ||
|---|---|---|
| Editing Notes | /pages/HYoMznMjYNcTiuBTwUAX | /files/mNPB1g74Ltoqhz2Kb4vY |
| Articulations | /pages/i69wiWjKve06woDIlZqb | /files/niVj6b5Qjhf2dDogzUcF |
| Expression Controls | /pages/SjZAciX2UGPjV8roPkXy | /files/aiZ7FEJgspRrHKba2mp0 |
| Unison Mode | /pages/rxx0wajaxO0NSQVyZQxx | /files/weyD8LUXjwqNLj2zyKkn |
Can I import MIDI or MusicXML files?
Yes. You can import your MIDI or MusicXML files into ACE Studio. For more information, please refer to [Import Files](/project/file-management/import-files).Can I control the articulations for specific instruments?
Yes. You can make the instrument's sound better match your requirements by using [Expression Controls](/ai-instruments/create-instrument-sounds/expression-controls).Smart
The AI automatically chooses the best articulation based on musical context.General
A standard, neutral playing style.Legato
Notes are played smoothly and connected, with no silence in between.Glissando
A continuous slide in pitch from one note to the next.Pizzicato
The strings are plucked with a finger instead of being bowed.Tremolo
A single note is repeated very rapidly, creating a trembling effect.Growl
A harsh, raspy, or guttural sound, common in jazz and rock.Scoop
Bending up to the target note from a slightly lower pitch.Arp-fall
A rapid, descending series of notes falling away from the main note.Mute
The sound is dampened or muted, creating a softer, less resonant tone.Vibrato
Vibrato is a subtle and rapid fluctuation in a note's pitch, which adds warmth, expression, and richness to the sound.Split-tones
Split-tones are an advanced technique that creates a rough, textured sound by producing multiple pitches simultaneously. It's perfect for adding a raw, edgy character or a sense of tension to your melody.# Audio Tracks Audio tracks in ACE Studio host audio clips and support audio recording. ## Overview When audio clips are present on a empty track, it becomes a Audio Track. Double-click on the empty area of the track to quickly import audio files. For more information, please refer to [Clips](/project/arrangement-in-canvas/clips). You can record sounds on Audio Tracks. For more information please refer to [Record](/project/arrangement-in-canvas/record). # Clips Clips are ACE Studio's fundamental units for organizing and editing audio and MIDI content and applying specialized tools. ## Overview
Editing content
Double click on the body of a clip to open the editor, where you can edit its content.Moving clips
After creating the selection, drag on the title bar to move the clip. If the selection only covers a part of the clip, this part will be split out while being moved.Deleting clips
After creating a selection, you can use Delete to remove the part covered by the selection. If the selection covers an entire clip, the clip will be completely deleted; if the selection only covers part of a clip, the portion of the clip covered by the selection will be trimmed.Adjusting length
Clips can have their length adjusted by dragging the left/right edges. You can also create a selection to delete a part of a clip.Fades & cross-fades
When hovering the cursor on a clip, there will be 2 little squares at the top left/right corner of the clip. Drag the square horizontally to create fade in/out for the clip. Drag on the handles on the fade curve to adjust the slope. When 2 clips are connected, dragging the square across clips will create a cross-fade.Splitting clips
There are 2 ways to split clips: * Split a clip at a specific position: Place the marker-line at where you would like to split, and use the split function from right-click menu. * Split out a piece from a clip: Create a selection to cover the piece you would like to split, and use the split function from right-click menu. Shortcut key Ctrl / ⌘Command + E .Deactivate clips
Deactivated clips are in dark color and will not be synthesized or heard. To deactivate a clip, you can: * Click on the title bar of the clip, and deactivate it from right-click menu. * Place the marker-line within a clip, and deactivate it from right-click menu. To deactivate a piece of a clip, you can: * Create a selection to cover the piece you would like to deactivate, and deactivate it from right-click menu. Shortcut key 0.Changing Colors
The color of a clip follows the color of its current track. You can assign a color for the clip from the right-click menu.# Chord Track Chord Track provides a global tool for creating chord progressions. The Chord Track is a special global track designed for creating and playing back chord progressions. It is a permanent part of your project, fixed at the top of the track list. The track has its own built-in piano sound, so you can hear the chords you create. You can control its playback with its dedicated Mute and Volume controls on the track header and [mixer](/project/mixing/mixer). To show or hide the Chord Track, click the Chord Track button in the track list header. ## Create Chords On the Chord Track, double-click on the grid where you want your progression to start. This will create a new chord clip, pre-filled with four default chords. ### Edit Chords * Select a chord within the clip to edit it. The Chord Editor will appear at the bottom. * In the editor, you can choose a root note and the chord quality (e.g., Major, minor, 7th). * To set a different bass note (inversion), click the "Bass" button and select a new bass note from the keyboard display. ### Adjust and Add Chords * Drag the right boundary of any chord to change its duration. * Click the + button that appears when you hover between or after chords to insert a new chord. * To make the entire chord progression longer, simply drag the right edge of the chord clip itself. ## Chord Loop Once you have created a chord progression you like, you can easily loop it. * Click the Loop + button located at the top-right corner of the chord clip. This will create the first loop of your progression. * After the first loop is created, you can simply drag the right boundary of the last looped section to extend the loops further across your timeline. ## Use Chord Progression As Background The Chord Track can serve as a powerful compositional guide by displaying its harmony in the background of the Piano Roll. This helps you write melodies and basslines that are in key with your chords. When editing notes, locate the Scale Mode setting in the Piano Roll toolbar. Switch the mode from "Scale" to "Chord". Once enabled, the notes of the current chord from the Chord Track will be highlighted on the Piano Roll grid. # Video Track Video Tracks in ACE Studio host video clips and support video-based scoring and sound design. ## Overview The Video Track is a special global track designed to align visuals with music and sound effects in the same timeline. You can control the video audio playback through the track header and the Mute, Solo, and Volume controls on the Mixer. To show or hide the Video Track, click the Video Track button in the track list header. ## Create a Video Track You can create a Video Track by: * Dragging a video file onto the Canvas. * Importing a video file into the project, then placing it on an empty track. If the video contains embedded audio, you can detach that audio and manage it separately on an audio track. ## Video Clip Management On a Video Track, you can: * Detach or reattach the audio. * Replace the video. * Adjust the video volume and apply fade-in and fade-out to the audio. Double-click a video clip to open the video monitor for preview. ## Working with Video Composer Video Composer is an AI tool that helps you create music and sound effects for a video inside ACE Studio. It analyzes the video, generates matching audio, and places the results on the timeline as editable clips. For more information, please refer to [Video Composer](/ai-tools/video-composer). # Mixing Mix tracks in ACE Studio to balance levels and apply effects. ## Overview Mixing is the art of blending all your individual tracks—vocals, instruments, and audio clips—into a single, cohesive piece of music. It's where you balance levels, position sounds in the stereo field, and apply effects to bring your song to life. In ACE Studio, the Mixing section is divided into two main areas: * [Mixer](/project/mixing/mixer) * [Effects](/project/mixing/effects) # Mixer Manage track volume, panning, and effects in Mixer. The Mixer provides detailed controls for every track in your project. It's a panel that expands from the left side of the track list, giving you access to volume, panning, effects, and routing for each track. To open or collapse the Mixer, click the Mixer icon in the main toolbar, or use the shortcut M.
| Control | What it does |
|---|---|
| Freq | Centre/corner frequency of the band. Displayed in Hz, switching to kHz above 1000. |
| Q | Bandwidth. Higher Q = narrower, more surgical; lower Q = broad and gentle. |
| Gain | Cut or boost at that frequency. |
| Preset | Use it for |
|---|---|
| Choir | Warmth and fullness — blended, layered vocals. |
| Backing | A supporting shape that sits a backing vocal behind the lead. |
| Lead | Clarity and presence — pushes a lead vocal forward. |
| Bright | Brilliance and air — adds top-end sparkle. |
| Control | What it does |
|---|---|
| Threshold (the line) | The level above which compression kicks in. Lower it to compress more of the signal. |
| Ratio | How hard it compresses above the threshold. 2:1 is gentle; 4:1 is firm; 8:1+ is heavy or limiting. |
| Attack | How fast it clamps down after a sound crosses the threshold. Fast catches transients; slow lets them through for punch. |
| Release | How fast it lets go once the signal drops. Too fast can pump; too slow stays ducked. |
| Gain (makeup) | Brings the level back up after compression has lowered it. Match the output to the bypassed level for a fair comparison. |
| Control | What it does |
|---|---|
| Threshold (the meter line) | How loud the sibilance has to get before it is turned down. Drag the line down to de-ess more aggressively. |
| Freq (crossover) | The frequency above which the de-esser listens for sibilance. Tune it to where the harshness sits — typically 5–9 kHz for most voices. |
| Listen (headphone button) | Solos the sibilance the de-esser is detecting, so you can hear exactly what you are targeting while you set the crossover and threshold. |
| Control | What it does |
|---|---|
| Gain | Drives the signal into the limiter. More gain = louder and more limiting. |
| Ceiling | The hard maximum output level — nothing gets past it. The ceiling line is shown on the monitor. |
| Attack | How fast it grabs peaks. Fast for transparent peak-catching. |
| Release | How fast it recovers. Too fast can distort; too slow ducks the level. |
| Preset | Character |
|---|---|
| Room | Small, tight, intimate. |
| Hall | Larger, longer, smoother — with more damping for a darker tail. |
| Church | Big and long, brighter tail. |
| Cinematic | Huge, the largest space — for dramatic, washy effects. |
# Music Enhancer Reimagine and enhance selected audio in ACE Studio with AI-guided transformations. ## What Is Music Enhancer The Music Enhancer is a creative tool that reimagines your existing music using AI. By drawing a selection box on the canvas, you can transform all the audio within that selection into an enhanced version. ## How to Use Music Enhancer Click the **Music Enhancer** button in the toolbar to open the generation window.
| Category | Model or feature | Billing unit | Credit cost |
|---|---|---|---|
| Music analysis | Music Analysis | Per request | ≈20 per minute |
| Image models | Midjourney | Per request | 20 |
| Image models | Nanobanana | Per request | 25 |
| Image models | GPT Image 2 | Per request | 15 |
| Image models | Qwen Image Multiple Angles | Per request | 7 |
| Video models | MiniMax-H3 | Per second | 22 |
| Video models | Seedance 2.0 (1080p) | Per second | 68 |
| Video models | Seedance 2.0 (720p) | Per second | 34 |
| Video models | Seedance 2.5 (1080p) | Per second | 136 |
| Video models | Seedance 2.5 (720p) | Per second | 68 |
| Video models | Lipsync 3 | Per second | 25 |
| Agent | Agent LLM Tokens | Based on actual token usage | Varies by task |
Music Video lives in the top-right corner
Put your music on the Canvas, then start the session
Choose your video style
Choose your aspect ratio
The song is analyzed automatically
Onboarding: a few decisions, one conversation
Pick one candidate as the base look
Scene references are empty environments
The creative plan
Every storyboard in place on the Canvas, ready to generate
Choose Promo Clip
Choose your aspect ratio
Describe your idea — and optionally upload a character
The Director suggests sections; the Sections row on the Canvas shows the analysis
Edit an image in the viewer
Browse an asset's versions from the Library
Add your own assets from the Library
# ACE Studio MCP Server Connect ACE Studio to AI clients through its experimental MCP server. ## ACE Studio MCP Server {% hint style="warning" %} #### Experimental Status The ACE Studio MCP Server is currently in **experimental phase**. **Please note:** * Some features and settings may not be fully implemented yet * Features and functionality may change * You may encounter bugs or performance issues during use * Usage guidelines and rate limits will be published when the stable version is released We are actively improving this feature. If you have any feedback or encounter issues, please contact us at [**support@acestudio.ai**](mailto:support@acestudio.ai). {% endhint %} The ACE Studio MCP server offers a rich toolkit enabling AI agents to autonomously navigate and execute creative edits. By giving AI agents comprehensive insight into every detail of your project, it empowers them to assist you in creating and editing songs with greater speed and creative freedom. [The Model Context Protocol](https://modelcontextprotocol.io/docs/getting-started/intro) (MCP) is an open standard that enables AI assistants to seamlessly connect with external applications and data sources. The ACE Studio MCP server implements this protocol to give AI agents direct access to your creative workspace. ### Quick Start #### Launch the ACE Studio MCP Server 1. Open **ACE Studio**. 2. Go to **Preferences → General → MCP Server**. 3. Choose a transport mode: **HTTP** or **STDIO**. > The transport mode you select here determines how your AI client connects to ACE Studio. See the sections below for details and client-specific configuration. Choose the appropriate configuration based on the transport mode you selected and your AI client. #### Streamable HTTP Mode In HTTP mode, ACE Studio runs a local MCP server at a fixed address. Your AI client connects to it over the network. **Server Address:** `http://localhost:21572/mcp` > **Technical Note**: The ACE Studio MCP Server uses the **Streamable HTTP transport protocol**. Keep this address for the next configuration step. **Claude Desktop** > ⚠ Setting up the ACE Studio MCP Server in Claude Desktop requires editing a JSON configuration file. If you're not comfortable with technical configuration, we recommend trying more user-friendly clients. **Configuration Steps:** 1. Install Node.js, if needed. * Visit [nodejs.org](https://nodejs.org) and download the LTS version. 2. Locate the Claude Desktop configuration file. * **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` * **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` 3. Edit the configuration file and add the following: ```json { "mcpServers": { "acestudio": { "command": "npx", "args": [ "mcp-remote", "http://localhost:21572/mcp" ] } } } ``` 4. Save the file and restart Claude Desktop. **Verify Connection:**\ Type in Claude: ``` Please check the current ACE Studio project information ``` If Claude returns project details, the connection is successful. **Cursor** You can directly add MCP server to Cursor by clicking [here](https://cursor.com/en-US/install-mcp?name=ACE-Studio\&config=eyJ1cmwiOiJodHRwOi8vbG9jYWxob3N0OjIxNTcyL21jcCJ9). Or manually set it up: 1. Open Cursor settings. 2. Find the **Tools & MCP** section. 3. Click **New MCP Server**. 4. Fill in the following JSON: ```json { "mcpServers": { "ACE-Studio": { "url": "http://localhost:21572/mcp", "headers": {} } } } ``` 5. Click **Save**. 6. Restart Cursor. **Verify Connection:**\ Type in Cursor Chat: ``` @acestudio What tracks are in the current project? ``` **VS Code via native MCP support** You can directly add MCP server to VS Code by clicking [here](https://insiders.vscode.dev/redirect?url=vscode%3Amcp%2Finstall%3F%7B%22name%22%3A%22acestudio%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22http%3A%2F%2Flocalhost%3A21572%2Fmcp%22%7D). Or manually set it up: 1. Create or edit `.vscode/mcp.json` in your workspace. 2. Add the following configuration: ```json { "servers": { "ACE-Studio": { "type": "http", "url": "http://localhost:21572/mcp" } } } ``` **VS Code via Cline** 1. Install the Cline extension. 2. Open extension settings. 3. Find the MCP Servers configuration section. 4. Add a new server: ```json { "mcpServers": { "ACE-Studio": { "url": "http://localhost:21572/mcp", "type": "streamableHttp", "headers": {} } } } ``` **Other Clients** For most clients, use these configuration settings: * **Transport type:** Streamable HTTP. Some clients may call this `Remote`. * **Server URL:** `http://localhost:21572/mcp` Or import MCP server with the following JSON: ```json { "mcpServers": { "ACE-Studio": { "url": "http://localhost:21572/mcp", "headers": {} } } } ``` #### STDIO Mode In STDIO mode, your AI client launches and communicates with the ACE Studio MCP server directly through standard input and output. This is simpler to set up. You do not need to start a server manually or use a network address. **Getting the Command:** 1. In ACE Studio, go to **Preferences → General → MCP Server**. 2. Set the mode to **STDIO**. 3. Click **Copy Command** to copy the server command to your clipboard. The copied command will look like this: ``` "/Applications/ACE Studio.app/Contents/Helpers/ace_mcp_server" --stdio ``` Use this command in the configuration steps below. {% hint style="info" %} The command path varies by OS. Use the exact command copied from ACE Studio in every client configuration below. {% endhint %} **Claude Desktop** STDIO is the native transport for Claude Desktop. You do not need extra tools like `mcp-remote`. 1. Locate the Claude Desktop configuration file. * **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json` * **Windows**: `%APPDATA%\Claude\claude_desktop_config.json` 2. Edit the configuration file and add the following: ```json { "mcpServers": { "acestudio": { "command": "/Applications/ACE Studio.app/Contents/Helpers/ace_mcp_server", "args": ["--stdio"] } } } ``` 3. Save the file and restart Claude Desktop. **Verify Connection:**\ Type in Claude: ``` Please check the current ACE Studio project information ``` If Claude returns project details, the connection is successful. **Cursor** 1. Open Cursor settings. 2. Find the **Tools & MCP** section. 3. Click **New MCP Server**. 4. Fill in the following JSON: ```json { "mcpServers": { "ACE-Studio": { "command": "/Applications/ACE Studio.app/Contents/Helpers/ace_mcp_server", "args": ["--stdio"] } } } ``` 5. Click **Save**. 6. Restart Cursor. **Verify Connection:**\ Type in Cursor Chat: ``` @acestudio What tracks are in the current project? ``` **VS Code via native MCP support** 1. Create or edit `.vscode/mcp.json` in your workspace. 2. Add the following configuration: ```json { "servers": { "ACE-Studio": { "command": "/Applications/ACE Studio.app/Contents/Helpers/ace_mcp_server", "args": ["--stdio"] } } } ``` **VS Code via Cline** 1. Install the Cline extension. 2. Open extension settings. 3. Find the MCP Servers configuration section. 4. Add a new server: ```json { "mcpServers": { "ACE-Studio": { "command": "/Applications/ACE Studio.app/Contents/Helpers/ace_mcp_server", "args": ["--stdio"] } } } ``` **Other Clients** For most clients, use these configuration settings: * **Transport type:** STDIO * **Command:** `/Applications/ACE Studio.app/Contents/Helpers/ace_mcp_server` * **Arguments:** `--stdio` Or import MCP server with the following JSON: ```json { "mcpServers": { "ACE-Studio": { "command": "/Applications/ACE Studio.app/Contents/Helpers/ace_mcp_server", "args": ["--stdio"] } } } ``` ### Usage Examples Once connected, you can try the following prompts to collaborate with your AI assistant: #### Create a New Project ``` Help me create a new pop-style project with BPM 120 in ACE Studio, in C major, add a lead vocal track and a violin accompaniment track ``` #### Generate Lyrics and Melody ``` Based on the theme "Summer memories by the sea," write an 8-bar chorus section in ACE Studio. The melody should be light and lively, using a pentatonic scale ``` #### Edit MIDI ``` In ACE Studio, add a piano chord progression in bars 9-16: C - Am - F - G, each chord lasting 2 bars ``` # Cloning A Voice for Vocal Synth Clone your own voice as a Vocal Synth voice in ACE Studio. ## What Is Vocal Synth Cloning? This is a feature to customize your own vocal synth model by uploading your vocal samples. AI will learn the timbre and singing style based on the samples you upload, and clone a digital version of your voice. After the customization, you can use your voice to generate vocals from MIDI and lyrics just like our pre-made AI voices in ACE Studio. {% hint style="success" %} Your cloned AI voice is private under your account, no one else can access it without your authorization. {% endhint %} ## How to Clone My Voice for Vocal Synth? ### Preparing Your Datasets
Clean Dry Vocals
High-quality voices require clean and dry vocal samples: * Without any reverb, delay, chorus effects * Without background noise * Without instrumentals or any non-human sounds * Without any harmonies or vocal doubles 30-100 mins of singing vocal samples are recommended for a voice. The more samples you provide, the more singing details AI can learn, but it brings fewer benefits when you reach over 120 minutes. > Room Reflections > > Vocals recorded with big room reflections might cause error recognitions and result in unexpected model performances. > Vocals from stem splitter > > When you are using vocal remover or stem splitter for vocals, the output quality might be damaged too low for training. For a higher quality voice model, please optionally use vocals from stem splitter.Recording Samples
**Quality microphone with audio interface** Professional microphones with audio interfaces bring high-quality vocals. You'll need recording software to connect to your interface, record, edit, and mix your vocals. When recording for a voice model, avoid microphones that are not built for singing: * Phone or laptop mics * Lapel or headset mics * Karaoke mics * Earphone mics or bluetooth earphones like air pods (these are usually for phone talks) **Recording environment** 1. Unwanted background noises can include people talking, electrical hums and buzzes, traffic and outdoor noise, as well as movements of accessories or objects. To prevent these noises from interfering with your recording, it is important to select a quiet location. Choose a place where you can minimize or eliminate unexpected noise disturbances. 2. Sound reflections can occur due to the presence of hard, level surfaces, resulting in reverberation or echoes in your recordings. This can give your tracks a hollow or distant quality, detracting from the desired intimacy and clarity. 3. Try clapping your hands sharply in the room and listen carefully. If you perceive a fluttering sound or a prolonged echo, it indicates the presence of reverb issues. 4. To address this, incorporate soft materials that can absorb sound. Consider using carpets, rugs, or thick curtains to significantly reduce reflections. Covering hard floors and, if possible, hanging curtains over windows, as well as placing furniture with fabric coverings in the room, can be beneficial. 5. Avoid using hard surfaces as they contribute to the problem. If you cannot afford professional acoustic panels, you can utilize everyday items such as canvas paintings, tapestries, or foam tiles to break up these surfaces. 6. When setting up your microphone, be mindful of its placement. Avoid positioning it too close to walls or in corners. Instead, aim for the center of the room or experiment with different locations to find the optimal spot with minimal reverb. **Headphone bleed** During recordings, particularly when capturing vocals, it is common for the audio from headphones to bleed into the microphone. This issue arises when the volume of the headphones is set too high or when open-back headphones are being used. This might be acceptable when recording for a song, but try to avoid this bleeding when recording for your voice model. **Microphone placement** For regular volume, it is recommended to position yourself about 2 inches away from the microphone. However, for louder phrases or when belting, it is advisable to increase the distance to around 4-6 inches. It is important to note that you should always stay closer than 12 inches from the microphone to maintain optimal audio capture. > Creating Space for Belting > > When engaging in belting techniques, it's important to allow yourself ample space, both in terms of microphone distance and the size of the room you're in. Excessive sound isolation, such as being confined in a closet or booth, or surrounding your microphone with foam, can easily result in overloading the microphone capsule. If you're unsure, it's advisable to incorporate more room sound when performing belted phrases.Singing Languages
**Basic custom slot** Only one singing language will be supported in your voice model trained under basic custom slot. **Pro custom slot** Your voice trained under pro custom slot can go multilingual. **Languages in your samples** During the training process, each sample file will be processed individually and treated as a single-language file. It is important to avoid mixing phrases from different languages within the same sample file. When uploading samples, please ensure that you place them under the appropriate language tab. Even if you are uploading samples for a basic custom slot, you have the flexibility to upload samples in different languages if needed. Keeping the samples organized by language will help maintain clarity and improve the training process. **Upcoming languages** We are continuously working on developing new singing languages for the custom voice feature. For your new voice: * New languages will be supported by new pro custom slots. * New languages will be one of the options to be supported by new basic custom slots. For your existing voice: * New languages will be supported when retraining your pro custom slots. * New languages will be optional when retraining your basic custom slots.Singing or Speech
Singing samples and speech samples can both be accepted for training your singing voice model. Your voice can learn: * Timbre from your singing samples and speech samples, but plase note: for a person, timbre of speaking can be different to singing, which usually can not represent the true performance of singing. * Singing style from your singing samples Your voice can't learn: * Singing style from your speech samplesFile Quality Settings
The audio quality of your samples directly impacts the quality of your voice. We recommend you to set your audio quality in: * Bit Depth = 16-bit * Sample Rate = 44.1khz or 48khz * Lossless file format (.wav or .flac)Post-Processing
To maintain the natural character and clarity of your target voice: * **No overlaps:** multi-layered vocals can complicate AI's analysis. Place the overlapped takes at back and stick to a single vocal track to ensure the AI can accurately process and learn from your samples. * **No hard cuts:** hard cuts can create abrupt starts or ends, which are not normal in a natural singing sound and can introduce clicks or pops. Use smooth fades at the beginning and end of the vocal clip for a more natural transition. * **No duplicating sections:** Duplicated sections don't help for the training. Your voice model benefits from the natural variation of performance. * **Control the volume:** Make sure your samples stay around 30-50% of your meter. Use a volume rider or automation to make sure volume levels are consistent across your entire dataset. The aim is to create a consistent volume level across the recording while keeping the dynamics within sections.Versions
AI learns incrementally from your data, analyzing each sample in a step-by-step process. As learning deepens, the number of steps increases. Training with a small or limited-quality dataset, such as one not designed for singing but for speech, may require only a few steps. In contrast, a larger and more diverse dataset might necessitate additional steps for a thorough fit. However, excessive training steps can lead to overfitting, potentially degrading the performance of your voice with unpredictable outcomes. By the end of training, you will get several versions based on different training steps from Rare to Well-done. You can find the best version by switching deployment and comparing each other.Blend Voices
Blending voices results in a hybrid voice. You can customize your voice to sound more like your target voice by adjusting the ratios of the blended voices. To do this, navigate to the slots management page and click the ‘blend voices’ button located under each version. After blending, your voice will adopt the new voice characteristics. To apply these changes, you will need to refresh your voice by restarting ACE Studio.Deploy to ACE Studio
For Basic custom slots and Pro custom slots, after deploying a version, you can switch deployment from one version to another. You need to re-launch ACE Studio after each deployment to refresh your voice library.Clean Dry Vocals
High-quality voices require clean and dry vocal samples: * Without any reverb, delay, chorus effects * Without background noise * Without instrumentals or any non-human sounds * Without any harmonies or vocal doubles 30-100 mins of singing vocal samples are recommended for a voice. The more samples you provide, the more singing details AI can learn, but it brings fewer benefits when you reach over 120 minutes. > Room Reflections > > Vocals recorded with big room reflections might cause error recognitions and result in unexpected model performances. > Vocals from stem splitter > > When you are using vocal remover or stem splitter for vocals, the output quality might be damaged too low for training. For a higher quality voice model, please optionally use vocals from stem splitter.Recording Samples
**Quality microphone with audio interface** Professional microphones with audio interfaces bring high-quality vocals. You'll need recording software to connect to your interface, record, edit, and mix your vocals. When recording for a voice model, avoid microphones that are not built for singing: * Phone or laptop mics * Lapel or headset mics * Karaoke mics * Earphone mics or bluetooth earphones like air pods (these are usually for phone talks) **Recording environment** 1. Unwanted background noises can include people talking, electrical hums and buzzes, traffic and outdoor noise, as well as movements of accessories or objects. To prevent these noises from interfering with your recording, it is important to select a quiet location. Choose a place where you can minimize or eliminate unexpected noise disturbances. 2. Sound reflections can occur due to the presence of hard, level surfaces, resulting in reverberation or echoes in your recordings. This can give your tracks a hollow or distant quality, detracting from the desired intimacy and clarity. 3. Try clapping your hands sharply in the room and listen carefully. If you perceive a fluttering sound or a prolonged echo, it indicates the presence of reverb issues. 4. To address this, incorporate soft materials that can absorb sound. Consider using carpets, rugs, or thick curtains to significantly reduce reflections. Covering hard floors and, if possible, hanging curtains over windows, as well as placing furniture with fabric coverings in the room, can be beneficial. 5. Avoid using hard surfaces as they contribute to the problem. If you cannot afford professional acoustic panels, you can utilize everyday items such as canvas paintings, tapestries, or foam tiles to break up these surfaces. 6. When setting up your microphone, be mindful of its placement. Avoid positioning it too close to walls or in corners. Instead, aim for the center of the room or experiment with different locations to find the optimal spot with minimal reverb. **Headphone bleed** During recordings, particularly when capturing vocals, it is common for the audio from headphones to bleed into the microphone. This issue arises when the volume of the headphones is set too high or when open-back headphones are being used. This might be acceptable when recording for a song, but try to avoid this bleeding when recording for your voice model. **Microphone placement** For regular volume, it is recommended to position yourself about 2 inches away from the microphone. However, for louder phrases or when belting, it is advisable to increase the distance to around 4-6 inches. It is important to note that you should always stay closer than 12 inches from the microphone to maintain optimal audio capture. > Creating Space for Belting > > When engaging in belting techniques, it's important to allow yourself ample space, both in terms of microphone distance and the size of the room you're in. Excessive sound isolation, such as being confined in a closet or booth, or surrounding your microphone with foam, can easily result in overloading the microphone capsule. If you're unsure, it's advisable to incorporate more room sound when performing belted phrases.Singing Languages
For a voice changer voice, you don’t need to keep all samples in one language.Singing or Speech
For a voice changer voice, there is no big difference between speech samples and singing samples. But for a singing voice changer voice, it is more suitable to use singing samples for training.File Quality Settings
The audio quality of your samples directly impacts the quality of your voice. We recommend you to set your audio quality in: * Bit Depth = 16-bit * Sample Rate = 44.1khz or 48khz * Lossless file format (.wav or .flac)Post-Processing
To maintain the natural character and clarity of your target voice: * **No overlaps:** multi-layered vocals can complicate AI's analysis. Place the overlapped takes at back and stick to a single vocal track to ensure the AI can accurately process and learn from your samples. * **No hard cuts:** hard cuts can create abrupt starts or ends, which are not normal in a natural singing sound and can introduce clicks or pops. Use smooth fades at the beginning and end of the vocal clip for a more natural transition. * **No duplicating sections:** Duplicated sections don't help for the training. Your voice model benefits from the natural variation of performance. * **Control the volume:** Make sure your samples stay around 30-50% of your meter. Use a volume rider or automation to make sure volume levels are consistent across your entire dataset. The aim is to create a consistent volume level across the recording while keeping the dynamics within sections.# Song Templates Discover and use community-created song templates. Creative Library Templates are pre-designed song structures created by the community, serving as a foundation for music production. These templates include arrangements, instrumentation, and other key elements, allowing you to build upon existing frameworks. ## Browse Templates
* Click + to select a voice or instrument. This will create a new track in ACE Studio and link it to this Bridge instance. * Alternatively, you can link this Bridge to an existing track.\  4. **Use Bridge in Auto Mode:** * **To Record MIDI:** When you play a part that has MIDI in your DAW, the Bridge will be in a **Record** state, capturing all MIDI from the track and sending it to ACE Studio in real-time.\  * **To Play Back Audio:** When you play a part that has clips in a linked ACE Studio track, the Bridge automatically switches to **Playback** state, streaming the synthesized audio from ACE Studio back to the DAW track.\  5. **Track Preview:** The clips and playhead position from the linked ACE Studio track are shown in this area. This allows you to see what's happening in ACE Studio without leaving your DAW. {% hint style="info" %} When you record MIDI from your DAW into ACE Studio, you will hear the piano sampler sound from the Bridge. {% endhint %} ## Multi-Instances You can now run multiple instances of ACE Bridge 2 on different MIDI tracks to control several ACE Studio tracks at once. * Each Bridge instance is independent. * A track in ACE Studio can only be linked to one Bridge instance at a time. ## Tempo Sync ### ARA Tempo Sync For rock-solid tempo, time signature, and transport synchronization, use the included **ACE Bridge ARA** plugin. **What it does:** * Perfectly syncs your DAW's tempo map and time signature changes to ACE Studio. * Allows bi-directional synchronization of ACE Studio's and the DAW's transport (play/stop/seek). **How to Set Up:** This requires attaching the ARA plugin to a "dummy" audio clip in your DAW. {% tabs %} {% tab title="Logic Pro" %} 1. To use ARA with Logic on Apple Silicon, launch Logic in **Rosetta mode**.
# Preferences Customize and manage ACE Studio's settings. For Windows users, you can find preferences under \[File] from the main menu. For Mac users, you can find preferences under \[ACE Studio] from main menu. You can also click the :gear: gear icon in the lower right corner to open preferences. ## General ### Language * **Interface**: Sets the display language for the entire user interface, including menus, buttons, and tooltips. By default, the application attempts to match your operating system's language. * **Default singing language**: Determines the default language assigned to any new vocal track you create. The "In Singer's Native Language" option will automatically set the track's language to match the native language of the singer you select. ### Auto Scroll These settings configure the automatic scrolling behavior of the timeline during playback, ensuring the playhead remains visible. * **Animation**: Customizes the style and speed of the auto-scroll animation when the view advances. * **Scroll Trigger**: Defines the point at which auto-scroll is activated. * **Scroll Dismiss**: Prevents auto-scrolling when you are zoomed in for detailed editing. For example, "<2.5s Scale" disables auto-scroll if the currently visible timeline represents less than 2.5 seconds, avoiding unwanted screen jumps. ### Debug * **Debug Logs**: Manages the storage of application log files, which can help developers diagnose issues. You can set how long logs are kept. ### MIDI Import * **Octave Offset**: Allows you to transpose all notes in an imported MIDI file up or down by one or more octaves. ### Plug-ins Use this section to manage ACE Bridge and third-party effect plug-ins. #### ACE Bridge Install or uninstall [ACE Bridge 2](/daw-integration/ace-bridge-2) here. If the plug-in stops working, reinstall it here. ACE Studio also notifies you when an update is available. > This setting applies only to **macOS**. On **Windows**, ACE Bridge 2 is installed with ACE Studio and can be restored by reinstalling ACE Studio. #### Rescan plug-ins Rescan third-party plug-ins — VST3 and AU — here. For supported formats, scan locations, and how to use plug-ins on the FX chain, see [Third-Party Effects](/project/mixing/effects/third-party-effects). ACE Studio scans your plug-in folders once and remembers the list, so it does not re-scan on every launch. When you install or update a plug-in, refresh the list here: * **Rescan**: Scans for newly installed or updated plug-ins and adds them to the **+ Insert** browser. * To rebuild the list from scratch, hold Alt / Option while clicking **Rescan** to force a full re-scan of all plug-ins. This is slower but resolves a plug-in list that has gotten out of sync. {% hint style="info" %} If a plug-in hangs or fails during the scan, you can **Disable** it — it won't be scanned again — or **Skip** it and continue. {% endhint %} ## Audio {% hint style="warning" %} For Windows users: Due to the exclusivity of ASIO, it can only support one program at a time. If you want to use an ASIO device, please make sure there is no other program using ASIO at the same time. For more information, please refer to[ASIO Problem?](/trouble-shooting) {% endhint %} ### Device This section controls which hardware and drivers the application uses for audio. * **Device Type**: Selects the audio driver model for communication with your hardware. > On **macOS**, this will typically be **CoreAudio**. > > On **Windows**, it is highly recommended to select **ASIO** if you have an audio interface with dedicated ASIO drivers, as it provides the lowest latency and best performance. * **Input**: Choose the device you will use for recording audio. * **Output**: Choose the device for audio playback. * **Output Channels**: If your selected output device has multiple physical outputs, you can choose which pair to use here. * **New device Notice**: When this box is checked, the application will notify you if it detects that an audio device has been connected or disconnected, prompting you to review your settings. ### Recording & Playback These settings fine-tune audio performance, quality, and recording behavior. * **Sample Rate**: Determines the digital audio quality. Higher values like 48000 Hz or 96000 Hz offer higher fidelity but result in larger file sizes. 44100 Hz is the standard for CDs, while 48000 Hz is common for video and professional audio. * **Buffer Size**: Controls the amount of data processed at once, directly impacting latency. * **Low Buffer Size** (e.g., 128, 256): Results in very low latency (delay), which is ideal for real-time recording and monitoring. However, it requires more CPU power and may cause clicks or pops on less powerful systems. * **High Buffer Size** (e.g., 512, 1024): Increases latency but makes playback more stable and less demanding on the CPU. This is ideal for mixing and playback when you are not recording. * **Latency Compensation**: Manually corrects any timing discrepancies between your live input and the project's playback. If you find your recordings are slightly out of sync with the beat, adjust this value in milliseconds (ms) until the recorded audio is perfectly aligned. * **Pre-count**: Sets a metronome count-in before [recording](/project/arrangement-in-canvas/record) begins. Selecting "1 Bar," for example, will play one bar of metronome clicks, giving you time to prepare before the recording starts on the downbeat. ## Rendering The **Rendering** tab allows you to configure how the application generates the synthesized vocal audio. The application supports two primary rendering modes: the default **Cloud Rendering** and the performance-enhancing **Turbo Mode**. These settings currently apply to vocal synth models Verse 2.6 and later. * **Test Turbo Mode:** Click this button to start a 1-minute performance benchmark. * **Turbo Mode**: Once unlocked by a successful performance test, you can use this checkbox to enable or disable Turbo Mode. * **Pre-rendering:** When checked, the application will proactively start rendering vocals in the background immediately after you finish editing a note or parameter. This means the audio is often ready to play before you even press the spacebar, resulting in a more responsive and seamless editing experience. For more information about rendering, please refer to [Local Rendering](/ai-rendering/local-rendering). ## Update You can update to the latest version of ACE Studio manually here. # License & Copyright ## General Terms ACE Studio does not claim copyright ownership over outputs generated by users. You may use outputs created with ACE Studio in commercial or non-commercial projects, unless a specific feature, model, voice, instrument, or third-party service states otherwise on this page. You are responsible for ensuring that you have the necessary rights to any materials you provide as input, including prompts, lyrics, reference audio, stems, video, and any other uploaded or referenced content. If input materials are provided without the necessary rights, ACE Studio cannot guarantee that the resulting outputs will be free from third-party claims. This page explains the license terms, usage scope, and exceptions for different ACE Studio features. ## Licenses for the Use of Vocal Synth Voices ### Royalty-Free Voices Most of our pre-made voices are royalty-free. You can check it by hovering your mouse on each AI voice. If you need a proof of license, just click on the “Generate a certificated license” button in the AI voice profile panel. In the pop-up window, you just need to input your name and click generate, a PDF file will be generated for you. If you need more help with certificates of voice license, please feel free to contact us through
| AI Voice Name | Third-Party Provider | Contact Information |
| 70D-Abyss Project | Nylis Co., Ltd | https://www.abyssproject.info/guideline |
| Luo Tian Yi | Vsinger | https://vsinger.com |
| Yan He | Vsinger | https://vsinger.com |
| Yuezheng Ling | Vsinger | https://vsinger.com |
| Yuezheng Longya | Vsinger | https://vsinger.com |
| Mo Qingxian | Vsinger | https://vsinger.com |
| Zhiyu Moke | Vsinger | https://vsinger.com |
English
| Phoneme in ACE | IPA | Type | | -------------- | ------------------ | ----------------- | | aa | ɔ/ɑ | vowel | | ae | æ | vowel | | ah | ʌ/ə | vowel | | ao | ɔ: | vowel | | eh | e | vowel | | er | ɝ | vowel | | ih | ı | vowel | | iy | i: | vowel | | uh | u | vowel | | uw | u: | vowel | | aw | au | vowel | | ay | aı | vowel | | ey | eı | vowel | | ow | əu | vowel | | oy | ɔı | vowel | | r | r | semivowel | | w | w | semivowel | | y | j | semivowel | | m | m | consonant | | n | n | consonant | | ng | ŋ | consonant | | l | l | consonant | | b | b | consonant | | p | p | consonant | | d | d | consonant | | dx | flap t （eg.butter） | consonant | | t | t | consonant | | g | g | consonant | | k | k | consonant | | zh | ʒ | consonant | | sh | ʃ | consonant | | z | z | consonant | | s | s | consonant | | f | f | consonant | | v | v | consonant | | dh | ð | consonant | | th | θ | consonant | | jh | dʒ | consonant | | dr | dr | consonant | | tr | tr | consonant | | ch | tʃ | consonant | | hh | h | consonant | | mv | m̩ | vocalic consonant | | nv | n̩ | vocalic consonant | | ngv | ŋ̍ | vocalic consonant |Spanish
| Phoneme in ACE | IPA | Type | | -------------- | --- | ----------------- | | i | i | vowel | | u | u | vowel | | e | e | vowel | | o | o | vowel | | a | a | vowel | | aj | a͡j | vowel | | ej | e͡j | vowel | | oj | o͡j | vowel | | uj | u͡j | vowel | | aw | a͡w | vowel | | ew | e͡w | vowel | | ow | o͡w | vowel | | ja | j͡a | vowel | | je | j͡e | vowel | | jo | j͡o | vowel | | ju | j͡u | vowel | | wa | w͡a | vowel | | we | w͡e | vowel | | wi | w͡i | vowel | | wo | w͡o | vowel | | w | w | semivowel | | j | j | semivowel | | l | l | consonant | | p | p | consonant | | b | b | consonant | | t | t | consonant | | d | d | consonant | | k | k | consonant | | g | ɡ | consonant | | ts | ʦ | consonant | | tss | t͡ʃ | consonant | | dzz | ʤ | consonant | | m | m | consonant | | n | n | consonant | | jj | ɲ | consonant | | nn | ŋ | consonant | | r | r | consonant | | for | ɾ | consonant | | bb | β | consonant | | f | f | consonant | | dd | ð | consonant | | s | s | consonant | | z | z | consonant | | ss | ʃ | consonant | | jsl | ʝ | consonant | | x | x | consonant | | gg | ɣ | consonant | | mv | m̩ | vocalic consonant | | nv | n̩ | vocalic consonant | | nnv | ŋ̍ | vocalic consonant |Chinese
| Phoneme in ACE | IPA | Type | | -------------- | ----- | ------------------- | | ii | z̩ | vowel | | iii | ʐ̩ | vowel | | i | i | vowel | | u | u | vowel | | v | y | vowel | | a | ä | vowel | | ia | jä | vowel | | ua | wä | vowel | | eh | e̞ | vowel | | e | ɤ | vowel | | uo | wo̞ | vowel | | o | ɔ | vowel | | io | jɔ | vowel | | ae | ɛ | vowel | | ie | je̞ | vowel | | ve | ɥœ | vowel | | ai | äi̯ | vowel | | iai | jäi̯ | vowel | | uai | wäi̯ | vowel | | ei | e̞i̯ | vowel | | iei | je̞i̯ | vowel | | uei | we̞i̯ | vowel | | ao | äu̯ | vowel | | iao | jäu̯ | vowel | | uao | wäu̯ | vowel | | ou | o̞u̯ | vowel | | iou | jo̞u̯ | vowel | | an | än̯ | vowel | | uan | wän̯ | vowel | | aen | ɛn̯ | vowel | | ian | jɛn̯ | vowel | | van | ɥɛn̯ | vowel | | en | ən̯ | vowel | | uen | wən̯ | vowel | | in | in̯ | vowel | | vn | yn̯ | vowel | | ang | äŋ̑ | vowel | | iang | jäŋ̑ | vowel | | uang | wäŋ̑ | vowel | | eng | əŋ̑ | vowel | | ueng | wəŋ̑ | vowel | | ing | iŋ̑ | vowel | | ong | oŋ̑ | vowel | | iong | joŋ̑ | vowel | | er | əɚ | vowel | | ar | äɚ | vowel | | uar | wäɚ | vowel | | y | j | semivowel | | w | w | semivowel | | r | ʐ /ɻ | semivowel/consonant | | b | p | consonant | | p | pʰ | consonant | | m | m | consonant | | f | f | consonant | | d | t | consonant | | t | tʰ | consonant | | n | n | consonant | | l | l | consonant | | z | ts | consonant | | c | tsʰ | consonant | | s | s | consonant | | zh | ʈʂ | consonant | | ch | ʈʂʰ | consonant | | sh | ʂ | consonant | | j | tɕ | consonant | | q | tɕʰ | consonant | | x | ɕ | consonant | | g | k | consonant | | k | kʰ | consonant | | h | x | consonant | | mm | m̩ | vocalic consonant | | nn | n̩ | vocalic consonant | | ng | ŋ̍ | vocalic consonant |Japanese
| Phoneme in ACE | IPA | Type | | -------------- | ------------- | ----------------- | | a | a | vowel | | i | i | vowel | | u | ɯᵝ | vowel | | e | e̞ | vowel | | o | o̞ | vowel | | ax | ḁ | voiceless vowel | | ix | i̥ | voiceless vowel | | ux | ɯ̥ᵝ | voiceless vowel | | ex | e̞̥ | voiceless vowel | | ox | o̞̥ | voiceless vowel | | w | ɰᵝ | semivowel | | y | j | semivowel | | k | k | consonant | | s | s | consonant | | sh | ɕ | consonant | | t | t | consonant | | ch | ˈt͡ɕ | consonant | | ts | t͡s | consonant | | n | n | consonant | | h | h | consonant | | f | ɸ | consonant | | m | m | consonant | | r | ɾ | consonant | | g | ɡ | consonant | | z | z | consonant | | j | j | consonant | | d | d | consonant | | b | b | consonant | | p | p | consonant | | ky | kʲ | consonant | | ty | tʲ | consonant | | ny | ɲ | consonant | | hy | ç | consonant | | my | mʲ | consonant | | ry | ɾʲ | consonant | | by | bʲ | consonant | | gy | ɡʲ | consonant | | py | pʲ | consonant | | dy | dʲ | consonant | | vy | vʲ | consonant | | kw | k | consonant | | gw | ɡ | consonant | | ng | ŋ | consonant | | ngy | ŋʲ | consonant | | v | v | consonant | | fy | ɸʲ | consonant | | rr | r | consonant | | nv | n̩ | vocalic consonant | | mv | m̩ | vocalic consonant | | cl | 促音（そくおん）「っ」「ッ | - |Korean
| Phoneme in ACE | IPA | Type |
|---|---|---|
| a | a | vowel |
| i | i | vowel |
| u | u | vowel |
| eu | ɯ | vowel |
| e | e | vowel |
| o | o | vowel |
| eo | ʌ | vowel |
| ax | ḁ | voiceless vowel |
| ix | i̥ | voiceless vowel |
| ux | u̥ | voiceless vowel |
| eux | ɯ̥ | voiceless vowel |
| ex | e̥ | voiceless vowel |
| ox | o̥ | voiceless vowel |
| eox | ʌ̥ | voiceless vowel |
| y | j | semivowel |
| w | w | semivowel |
| g | k | consonant |
| gy | kʲ | consonant |
| gw | kʷ | consonant |
| n | n | consonant |
| ny | nʲ | consonant |
| nw | nʷ | consonant |
| d | t | consonant |
| dy | tʲ | consonant |
| dw | tʷ | consonant |
| r | ɾ | consonant |
| ry | ɾʲ | consonant |
| rw | ɾʷ | consonant |
| m | m | consonant |
| my | mʲ | consonant |
| mw | mʷ | consonant |
| b | p | consonant |
| by | pʲ | consonant |
| bw | pʷ | consonant |
| s | s | consonant |
| sy | sʲ | consonant |
| sw | sʷ | consonant |
| j | tɕ | consonant |
| jy | tɕʲ | consonant |
| jw | tɕʷ | consonant |
| ch | tɕʰ | consonant |
| chy | tɕʰʲ | consonant |
| chw | tɕʰʷ | consonant |
| k | kʰ | consonant |
| ky | kʰʲ | consonant |
| kw | kʰʷ | consonant |
| t | tʰ | consonant |
| ty | tʰʲ | consonant |
| tw | tʰʷ | consonant |
| p | pʰ | consonant |
| py | pʰʲ | consonant |
| pw | pʰʷ | consonant |
| h | h | consonant |
| hy | ç | consonant |
| hw | hʷ | consonant |
| gg | k͈ | consonant |
| ggy | k͈ʲ | consonant |
| ggw | k͈ʷ | consonant |
| dd | t͈ | consonant |
| ddy | t͈ʲ | consonant |
| ddw | t͈ʷ | consonant |
| bb | p͈ | consonant |
| bby | p͈ʲ | consonant |
| bbw | p͈ʷ | consonant |
| ss | s͈ | consonant |
| ssy | s͈ʲ | consonant |
| ssw | s͈ʷ | consonant |
| jj | t͈ɕ | consonant |
| jjy | t͈ɕʲ | consonant |
| jjw | t͈ɕʷ | consonant |
| pc | p̚ | coda consonant |
| tc | t̚ | coda consonant |
| kc | k̚ | coda consonant |
| ngc | ŋ | coda consonant |
| mc | m | coda consonant |
| nc | n | coda consonant |
| lc | ɭ | coda consonant |
| nv | n̩ | vocalic consonant |
| mv | m̩ | vocalic consonant |
| ngv | ŋ̍ | vocalic consonant |
French
| Phoneme in ACE | IPA | Type | | -------------- | --- | --------- | | p | p | consonant | | b | b | consonant | | t | t | consonant | | d | d | consonant | | k | k | consonant | | g | ɡ | consonant | | qm | ʔ | consonant | | tss | t͡ʃ | consonant | | dzz | d͡ʒ | consonant | | m | m | consonant | | n | n | consonant | | jj | ɲ | consonant | | nn | ŋ | consonant | | f | f | consonant | | v | v | consonant | | s | s | consonant | | z | z | consonant | | ss | ʃ | consonant | | zz | ʒ | consonant | | rr | ʁ | consonant | | j | j | semivowel | | l | l | consonant | | hh | ɥ | semivowel | | w | w | semivowel | | i | i | vowel | | y | y | vowel | | u | u | vowel | | e | e | vowel | | two | ø | vowel | | o | o | vowel | | ee | ɛ | vowel | | nin | œ | vowel | | oo | ɔ | vowel | | a | a | vowel | | aa | ɑ | vowel | | eh | ə | vowel | | onp | ɔ̃ | vowel | | eenp | ɛ̃ | vowel | | ninnp | œ̃ | vowel | | anp | ɑ̃ | vowel |Italian
| Phoneme in ACE | IPA | Type | | -------------- | --- | --------- | | p | p | consonant | | b | b | consonant | | t | t | consonant | | d | d | consonant | | k | k | consonant | | g | g | consonant | | ts | t͡s | consonant | | dz | d͡z | consonant | | tss | t͡ʃ | consonant | | dzz | d͡ʒ | consonant | | m | m | consonant | | n | n | consonant | | jj | ɲ | consonant | | nn | ŋ | consonant | | r | r | consonant | | for | ɾ | consonant | | f | f | consonant | | v | v | consonant | | s | s | consonant | | z | z | consonant | | ss | ʃ | consonant | | j | j | semivowel | | w | w | semivowel | | l | l | consonant | | ll | ʎ | consonant | | i | i | vowel | | u | u | vowel | | e | e | vowel | | o | o | vowel | | ee | ɛ | vowel | | oo | ɔ | vowel | | a | a | vowel |Portuguese
| Phoneme in ACE | IPA | Type | | -------------- | ----- | --------- | | p | p | consonant | | b | b | consonant | | t | t | consonant | | d | d | consonant | | k | k | consonant | | g | g | consonant | | tss | t͡ʃ | consonant | | dzz | d͡ʒ | consonant | | m | m | consonant | | n | n | consonant | | jj | ɲ | consonant | | for | ɾ | consonant | | f | f | consonant | | v | v | consonant | | s | s | consonant | | z | z | consonant | | ss | ʃ | consonant | | zz | ʒ | consonant | | x | x | consonant | | j | j | semivowel | | w | w | semivowel | | l | l | consonant | | ll | ʎ | consonant | | i | i | vowel | | u | u | vowel | | ii | ɪ | vowel | | e | e | vowel | | o | o | vowel | | ee | ɛ | vowel | | oo | ɔ | vowel | | six | ɐ | vowel | | a | a | vowel | | inp | ĩ | vowel | | unp | ũ | vowel | | enp | ẽ | vowel | | onp | õ | vowel | | sixnp | ɐ̃ | vowel | | eenp | ɛ̃ | vowel | | anp | ã | vowel | | uj | u͡j | vowel | | ej | e͡j | vowel | | oj | o͡j | vowel | | eej | ɛ͡j | vowel | | ooj | ɔ͡j | vowel | | aj | a͡j | vowel | | iw | i͡w | vowel | | ew | e͡w | vowel | | eew | ɛ͡w | vowel | | oow | ɔ͡w | vowel | | aw | a͡w | vowel | | ujnp | ũ͡j̃ | vowel | | ejnp | ẽ͡j̃ | vowel | | ojnp | õ͡j̃ | vowel | | sixjnp | ɐ̃͡j̃ | vowel | | ownp | õ͡w̃ | vowel | | awnp | ã͡w̃ | vowel |{% stepper %} {% step %} ### Import your MusicXML file ACE Studio support MusicXML as .mxl or .musicxml. You can directly import the MusicXML file by drag and drop. {% hint style="info" %} Learn more: [Import Files](/project/file-management/import-files). {% endhint %} {% endstep %} {% step %} ### Check all lyrics and musical settings After importing your MusicXML, check all the lyrics imported from the file, and check if the tempo is right. {% hint style="info" %} If your song has multiple tempos or time signatures, you can create change marks on the time ruler. To learn about how to insert a tempo mark or a time signature mark: [Tempo & Signature Change](/project/arrangement-in-canvas/tempo-and-signature-change). Learn more about editing lyrics: [Editing Lyrics](/ai-vocal-synth/creating-ai-vocals/editing-lyrics). {% endhint %} {% endstep %} {% step %} ### Choose AI voices Choose the right voice for each vocal track by dragging an AI voice from the voice library on the track head. * If you don’t want too much vibrato on the vocal, you can use the modulation tool to make the pitch curve more flat. For more details, please refer to [Editing Pitch](/ai-vocal-synth/creating-ai-vocals/editing-pitch). * For a STAB choir, here are some recommendations to our AI voices: * Ember Rose - Pop female voice, soprano * Clara Epic - Cinematic female voice, soprano * Karolyn - Opera female voice, soprano * Zalo - Gospel female voice, alto * Jessica - Gospel female voice, alto * Aaron - Opera male voice, tenor * Robert - Opera male voice, baritone * Drex L - Pop male voice, tenor * Felix - Mexican male voice, baritone {% endstep %} {% step %} ### Share with a link After fine-tuning your work, click on the Share button at the transport to upload your project as stems and create a link. So you can send this link to all your choir members, and let them rehearse this song with any devices. {% hint style="info" %} Learn more: [Share Projects](/project/file-management/share-projects) {% endhint %} {% endstep %} {% endstepper %} # Song Writing Easily write songs in ACE Studio by recording hummed melodies and refining them with AI tools. In ACE Studio, you can easily write songs. Start by preparing and importing chords or beats, then record your hummed melodies. Next, AI tools will convert your audio into MIDI and lyrics. Finally, meticulously edit the lyric content to help you craft perfect original works. {% stepper %} {% step %} ### Prepare your chords or beat You can prepare a beat track on your DAW, and import the beat track back to ACE Studio. (Remember to set up the same tempo) Or you can just create [chord](/project/arrangement-in-canvas/chord-track) progressions inside ACE Studio. {% endstep %} {% step %} ### Record your humming With chords or beat set up, you can [record](/project/arrangement-in-canvas/record) your humming inside ACE Studio. {% endstep %} {% step %} ### Test and fine-tune your melody Based on your recordings, you can convert them into MIDI and lyrics with our “[Vocal to MIDI and lyrics](/ai-tools/vocal-to-midi)” tool. Then you can edit the melody and lyrics in the piano roll, and hear the vocal result with our AI voices. {% endstep %} {% step %} ### Build lyrics on it Now you have the perfect topline, it’s time to build lyrics on it. You can edit lyrics line by line, or use the lyrics panel to edit whole lyrics together in the lyrics editor window. {% hint style="info" %} To learn more details about editing lyrics, please refer to [Editing Notes](/ai-vocal-synth/creating-ai-vocals/editing-notes). {% endhint %} If you want others to write the lyrics, you can save the project and send the project pack to them. Just remember to move your audio files under the “samples” folder. For more details, please refer to [File Management](/project/file-management). {% endstep %} {% endstepper %} # How to Fine-tune the Pitch Curve Learn to fine-tune the pitch curve in ACE Studio for diverse vocal expressions and effects. ## Aggressive pitch
# Don't Duplicate! Use Vocal Doubles # Can I Still Use My Old Projects? # "Where Did My Favorite Features Go?" — A 'Before & After' Guide # ASIO Problem? Resolve ASIO conflicts in ACE Studio for smooth audio playback with your DAW. ## Exclusivity in ASIO Whether ACE Studio or any DAW, playback works perfectly under ASIO mode when it's the only application that output sounds. But things may become unexpected when two applications both want to use an ASIO device at the same time. Most ASIO drivers can only serve one application at the same time due to the purpose of low latency. That means ACE Studio may fail to initialize ASIO driver and not be able to playback when your DAW has been using it, conversely, your DAW may fail to playback when ACE Studio already launched under ASIO mode. ## Solutions #### **Use ACE Bridge 2** ACE Bridge 2 is a VST3 instrument plugin for building an audio bridge between ACE Studio and your DAW. It can be installed together with ACE Studio. With ACE Bridge 2 connected between ACE Studio and your DAW, ACE Studio's playback will be sent directlly to the track in your DAW where ACE Bridge 2 lies, and no audio device will be used by ACE Studio until ACE Bridge 2 is off. In this case, you can hear all sounds come from your DAW with any configured ASIO device. {% hint style="info" %} Please note:If you launch ACE Studio first and select an ASIO device for its audio device before launching your DAW, your DAW may still have problem with playback even the ACE Bridge 2 is on. In this case, you could change the audio device into None in ACE Studio before launching your DAW. {% endhint %} #### **Try ASIO4ALL** ASIO4ALL is an universal ASIO driver, which utilizes low-level WDM drivers to achieve low-latency while keeping a wide compatibility device range. It implements a multi-client ASIO device, a.k.a ASIO4ALL can be used simultaneously by different DAWs. For how to install and use ASIO4ALL, and more general information on it, please consult their official website: