Music Generator is AIUNIFY PROS SUITE’s dedicated AI music-creation workspace.
The current user interface identifies the workspace as:
AI Music Studio
with the description:
“Turn your ideas into professional-grade soundtracks with Suno V5”.
AI Music Studio currently supports:
Unlike the Standard AI Generator, Music Generator creates audio through a specialized music-generation service rather than through the normal text-generation workflow.
Navigate to:
Sidebar → Core Tools → Music Generator
The verified route is:
/music-generator
and the Sidebar currently marks Music Generator as a New Core Tool.
The /music-generator page verifies that you are signed into AIUNIFY PROS SUITE.
If you are not authenticated, the page redirects toward:
/login.
The Music Generator workspace is also wrapped in:
FeatureGuard → music-generator.
Therefore, being signed in does not by itself guarantee access.
Your account must also have access to the feature under the normal PROS SUITE Plan/tool-access rules described in Chapter 8.
Music Generator does not use the Standard AI Generator interface from Chapter 12.
Instead, it has its own specialized interface with:
This is important because the normal Standard Generator assumptions do not automatically apply.
At the top of the workspace, the interface displays:
AI Music Studio
and:
“Turn your ideas into professional-grade soundtracks with Suno V5”.
Two informational badges also appear:
The current user interface visibly labels the Music Studio:
48kHz Stereo.
However, the supplied user-operations source does not independently inspect the downloaded audio file's encoding or sample-rate metadata.
Therefore, this manual records 48kHz Stereo as the current product-interface designation rather than making a separate technical verification of each generated file.
AI Music Studio contains two primary tabs:
Create new music.
Review previously generated music associated with your account.
The default tab is:
Studio
This is where you configure and generate a new track.
The second tab is:
My Creations.
When saved music exists, a numeric badge beside My Creations displays the number of music assets currently loaded for your account.
The primary music-generation form is titled:
Configuration
with:
“Customize your track's style, lyrics, and metadata”.
At the top-right of Configuration are:
These modes change how the primary Prompt is interpreted and how much text you can enter.
In Normal mode, the primary field is labeled:
Music Description.
Use it to describe the music you want AIUNIFY to create.
The current example is:
“e.g. A lo-fi hip hop beat with a jazzy piano melody, cozy atmosphere for studying...”
This demonstrates the type of natural-language direction the generator accepts.
Normal Mode supports up to:
500 characters.
The current interface displays a character counter such as:
125 / 500
while you write.
A useful music description can identify:
For example:
Cinematic electronic soundtrack with deep synth bass, atmospheric pads, dramatic strings, gradual build, confident business-tech energy, and a powerful modern ending.
A Prompt such as:
Make a song.
gives the music engine very little creative direction.
A more descriptive Prompt usually gives the generator a clearer target.
For example:
Upbeat futuristic corporate electronic track with punchy drums, warm bass, bright synth arpeggios, subtle orchestral strings, confident inspirational mood, polished commercial production.
This communicates several independent musical qualities.
Selecting:
Custom
changes the main input label from:
Music Description
to:
Lyrics.
Use Custom Mode when you want to provide the song's lyrical content yourself.
The Custom Mode field displays:
“Enter your song lyrics here...”
Custom Mode supports up to:
5,000 characters.
This is substantially larger than the 500-character Normal Mode description.
Think of the modes as:
Describe the music you want.
Provide the Lyrics you want used.
Both modes also support Style/Genre, Title, Instrumental Mode, and Music Model settings.
A Custom Mode input might be structured as:
[Verse 1]
...
[Chorus]
...
[Verse 2]
...
[Bridge]
...
The exact musical interpretation remains dependent on the music-generation provider.
Below the main Prompt is:
Style / Genre.
The placeholder is:
“e.g. Synthwave, 80s, Dark”
Style can be used to further define the sound separately from the main description or Lyrics.
Examples include:
You can also combine descriptors.
Example:
Cinematic, orchestral, futuristic, inspirational
The Music-generation action accepts Style as an optional field.
A track can therefore be generated without manually entering Style, provided the primary Prompt contains content.
Beside Style / Genre is:
Title
with the placeholder:
Track Name.
Use this to identify the composition.
The server accepts Title as an optional generation parameter.
You can therefore generate without entering one.
If no Title was entered, newly generated tracks are displayed as:
Gen Track #1
Gen Track #2
and so forth in the immediate result area.
If no Style was entered, a newly generated result displays:
Original Composition.
The Configuration panel contains:
Instrumental Mode
with:
“Generate without any vocals”.
Turn this on when you want music without vocals.
The initial source state is:
instrumental = false.
Therefore, Instrumental Mode must be explicitly enabled if you want to request a no-vocal composition.
The current interface technically allows Custom Mode and Instrumental Mode to be selected at the same time.
Both:
instrumental: truecan be sent to the generation provider.
The supplied source does not establish which input takes precedence when those instructions conflict.
For predictable results, use Instrumental Mode primarily when vocals/Lyrics are not needed.
AI Music Studio has its own AI Model selector.
This is separate from the general PROS SUITE language-model selector described in Chapter 10.
The current Music Studio offers:
The current default is:
V5.
The UI identifies that as:
Suno V5 (Highest Quality).
This distinction is important.
Used by many language/reasoning AI workflows.
Used specifically by Music Generator.
MusicGeneratorPage does not use the Header's selectedModel; it maintains its own local Suno Model selection and sends that music Model directly into generateMusicAction.
Selecting a different OpenAI, Gemini, NVIDIA, Anthropic, or other language Model in the PROS SUITE Header does not replace:
inside the Music Studio.
Choose the desired Suno Model inside Music Generator itself.
When Music Studio is idle, the right side displays several clickable Style suggestions:
Selecting one of those suggestion badges places its text into:
Style / Genre.
It does not automatically start generation.
You can customize the Style after selecting it.
Before music has been generated, the output side displays:
Ready to compose?
with:
“Configure your track on the left and hit generate to start your journey into AI music.”
When your configuration is complete, select:
Generate Music.
Music Generator will not start if the main Prompt is blank.
If you try, the current interface displays:
Prompt Required
with:
“Please enter a description or lyrics for your music.”
The Generate Music button is disabled when:
Music Studio sends:
Music generation does not necessarily return finished audio immediately.
Instead, PROS SUITE:
The Music Studio recognizes the following internal/user-facing stages:
While the track is being created, the Generate button changes to:
Composing...
During Queuing, Generating, or Processing, the output area shows a status Card such as:
Queuing...
Generating...
or:
Processing...
The status Card states:
“Our AI is composing your unique track. This usually takes 30-60 seconds.”
Treat this as interface guidance, not a guaranteed completion time.
Provider availability and workload can affect actual completion.
After a Task ID has been created, the current Music Studio checks the Task approximately every:
3 seconds.
This polling updates the visible generation state.
The visual progress bar currently displays approximately:
rather than reading an exact percentage from the provider.
Therefore:
The progress bar is a visual status indicator, not a precise measurement of how much of the audio has been rendered.
When the provider returns one or more audio results, Music Studio changes to Success and displays:
Music Generated!
with:
“Your masterpiece is ready to listen.”
Completed tracks appear under:
Generated Masterpieces.
The Music Generator is designed to accept an array of result URLs.
Therefore, one generation Task can return more than one audio version.
Each returned URL is displayed as its own result Card.
When generation succeeds, the persistence workflow loops through all returned music URLs and saves each new result as a music asset for the signed-in user.
This is why one generation can create multiple entries in My Creations.
Each immediate result Card includes:
Hover over the generated track and select the Play button.
Music Studio loads the audio URL into its hidden Audio player and begins playback.
While a track is playing, the Play control changes to:
Pause.
Select it to pause the current track.
If you select the same track again after pausing it, Music Studio resumes playback using the same Audio element.
Selecting a different track:
When the hidden Audio element reaches the end, Music Studio sets its playback state back to not playing.
Generated result Cards display animated waveform-like bars while music is playing.
These bars are decorative UI animation.
They are not source-verified as a visualization calculated from the actual audio waveform.
The Music Generator's current result Cards provide Play/Pause but do not establish a user-facing:
for generated results.
Do not expect full media-player controls in the current Studio interface.
Each generated result includes:
Download.
The current Download button calls:
window.open(audioURL, '_blank')
rather than constructing and automatically saving a local file.
Therefore:
Download currently opens the generated audio URL in a new browser tab.
Depending on the browser and audio host, you may then be able to play or save the audio using the browser's normal controls.
Music Studio does not currently define a generated local filename such as:
my-song.mp3
inside its Download handler.
The resulting filename or Save behavior can therefore depend on the audio host/browser.
The current user interface does not provide a selector for:
The Music Generator receives audio URLs from the provider.
Do not claim a specific file format unless the opened/downloaded file itself confirms it.
After successful generation, the result area provides:
New Track.
Select it to return the generation display to its Idle state.
The current New Track handler only changes the Status back to:
idle.
It does not explicitly clear:
This can make it convenient to create another variation using similar settings.
When you actually start another generation, Music Studio:
before creating the next task.
Previously persisted music should still remain under My Creations.
The server-side generation action obtains the current Music Generator cost from:
settings.aiLimits['music-generator']
and if no configured value exists, uses:
100 Tokens.
This execution path is more directly relevant to actual Music Generator usage than the generic feature-card catalogue.
The general PROS SUITE feature catalogue currently lists:
Music Generator — 20 Tokens.
However, the actual Music-generation action uses:
Configured music-generator cost → otherwise 100 Tokens.
Therefore:
Do not rely on the generic 20-Token feature-card value as the guaranteed Music Generator charge.
The server-side Music Generator setting is the more direct operational source.
The current Music Studio Configuration panel does not display:
X tokens per generation
beside the Generate Music button.
Therefore, users should monitor:
Monthly Tokens
and any current account/Plan usage information.
Before creating the provider Task, the Music-generation action checks the signed-in user's PROS SUITE Token Balance.
If the balance is lower than the current generation cost, it returns:
“Insufficient tokens. Please top up your balance.”
The current server workflow is:
Check Balance
↓
Ask provider to create Music Task
↓
If Task creation succeeds:
Deduct PROS SUITE Tokens
↓
Persist Task
If the music provider does not successfully create a Task ID, the action returns:
Failed to start music generation
or the provider's message.
The Token-deduction line has not yet been reached at that point.
A Task can also fail later after it was successfully created and Tokens were already deducted.
The supplied source marks that Task as Failed but does not establish an automatic Token refund in that later-failure workflow.
Accordingly, this manual does not promise a refund for a provider Task that fails after successful creation.
When music generation completes successfully, the Music Studio explicitly refreshes the user's account information.
This allows updated account balance information to appear elsewhere in PROS SUITE.
Music generation relies on an external music-generation provider.
A provider-side error containing wording such as:
Credits insufficient
should not automatically be interpreted as the same thing as your:
PROS SUITE Monthly Tokens.
The two resource systems can be separate.
If the provider reports a failed state, Music Studio displays:
Generation Failed
and the provider error when available.
The source contains a special case for a particular demo-domain environment.
In that environment, provider credit exhaustion can display:
“In the demo, we are not accepting this request.”
This should not be confused with the normal production account Token message.
That same specific demo environment blocks new music generation and displays:
“In the demo, we are not accepting this request.”
with:
“Please contact us to get access.”
This is environment-specific behavior, not the general production workflow.
If creation fails, the result area displays:
Generation Failed
followed by the current Error.
The Failure Card contains:
Try Again.
Selecting it returns the display to Idle.
The Try Again button only changes the Status back to Idle.
Review your settings and then select:
Generate Music
when ready to submit another request.
When a provider Task starts successfully, PROS SUITE attempts to save the Task with metadata including:
When generation later succeeds, PROS SUITE saves each returned result URL as a:
music
asset associated with the signed-in user's account.
This supplies the data for:
My Creations.
Select:
My Creations
to view previously persisted Music Generator results.
Inside My Creations, the workspace is titled:
Generation History
with:
“All your previous musical creations in one place”.
The history service retrieves music assets where:
user_email equals the signed-in usertype equals musicand orders them by newest creation first.
Unlike AI Chat or Browser Control's temporary page-state conversations, Music Generator has a source-verified persisted music-asset history.
You can leave the Music Generator and later return to load previous saved music assets.
My Creations provides:
Refresh History.
Select it to retrieve the latest music assets again.
While history is loading, the button displays:
Refreshing....
While initial history is loading, AI Music Studio shows placeholder Cards representing the incoming music items.
Each saved music Card can display:
Each history Card displays the Model saved in the asset metadata.
If no Model metadata exists, the Card falls back to:
Suno V5.
A history Card determines its displayed title using:
If Style metadata exists, it appears below the Title.
Otherwise, the History Card displays:
Original Audio.
Each saved music Card displays the asset's local formatted creation date when available.
Hover over a saved Creation and select Play.
The same internal Audio player used for new results handles playback.
When a saved track is playing, a small animated visualization appears in its Card.
As with the immediate result visualization, this is UI animation rather than a source-verified analysis of the real audio waveform.
Saved history Cards contain:
Save.
Like the immediate Download control, Save calls:
window.open(asset.url, '_blank').
Therefore it opens the source audio in a new browser tab rather than performing a source-defined direct local-file download.
The current My Creations interface does not establish a:
control.
Music history Cards currently provide:
but not Delete.
The current My Creations interface also does not provide:
Rename Track
or an Edit Metadata dialog.
Title and Style are retained from the original generation metadata.
The supplied Music Studio source does not establish:
for My Creations.
The current Generation History does not provide a user-facing:
Music assets are shown newest-first.
The current user-side history action requests all of the signed-in user's music assets and the UI renders the returned collection.
There is no source-verified Load More or page-number control.
If no persisted music exists, My Creations displays:
No creations yet
and:
“Start by generating your first track in Normal or Custom mode.”
Below the current generation result area is:
Audio Isolation Pro
with:
“Need to separate vocals from background music? Our ElevenLabs-powered tool can isolate stems from any track with studio precision.”
An Isolation control appears on:
Select the Wand/Isolate control on the desired track.
The current interface displays:
Starting Isolation
with:
“Processing your audio with ElevenLabs...”
The source sends Audio Isolation through an:
ElevenLabs audio-isolation
provider task.
The Audio Isolation workflow sends the selected track's:
audio URL
into the provider.
There is no separate file-upload field inside the current Music Studio Isolation workflow.
If the provider creates an Isolation Task successfully, the interface displays:
Task Created
with:
“Isolation task started: [task ID]. You will see it in history soon.”
The interface tells users that the Isolation Task will appear in history.
However, the supplied source directly verifies My Creations retrieval only for assets whose Type is:
music.
The callback/API implementation responsible for final Isolation-result persistence is outside the sanitized User Operations bundle.
Therefore, this manual does not make a stronger claim about exactly how completed isolated stems will appear in My Creations.
The isolation action obtains its cost from:
settings.aiLimits['audio-isolation']
and otherwise falls back to:
50 Tokens.
If your PROS SUITE balance is below the current Isolation cost, the server returns:
“Insufficient tokens for audio processing.”
The current isolation flow is:
Check Token Balance
↓
Create ElevenLabs Isolation Task
↓
If successful:
Deduct Audio-Isolation Tokens
If Audio Isolation cannot start, Music Studio displays:
Isolation Failed
with the returned Error message.
The current Music Studio does not provide user controls for selecting specific isolation options such as:
The current UI simply submits the selected audio to the configured Audio Isolation service.
Audio Isolation operates from a generated/saved Music Generator audio URL.
The current MusicGeneratorPage does not provide a separate:
Upload Audio File to Isolate
control.
The source-defined Music Generator sends requests to a Suno-compatible generation service and receives a Task ID.
The application then polls the provider for status and extracts returned audio URLs.
For user operation, the important concept is:
Generate Music → Task Processing → Audio Results
Task IDs are handled internally by PROS SUITE.
Ordinary users do not need to:
Those are internal application operations.
The provider may return audio information using several response structures.
PROS SUITE normalizes usable returned audio URLs into a common result list.
The user simply sees the completed tracks.
Before writing the Prompt, decide:
Use Normal.
Use Custom.
This prevents unnecessarily rewriting the request after generation.
Instead of:
A song about business growth.
consider:
Energetic modern electronic-pop track about business growth, confident male/female vocal feel, uplifting chorus, driving drums, polished corporate-commercial production.
Musical direction gives the provider more guidance.
For example:
Music Description
Inspirational technology brand anthem with an energetic build and powerful ending.
Style / Genre
Cinematic electronic, modern corporate, synthwave
This separates concept from sonic identity.
A clear Title helps identify the track later in:
My Creations.
For example:
Built for Business
is easier to recognize than a generic fallback Name.
Check the Music-specific Model before selecting Generate.
Changing the Header AI Model will not change the Suno Model.
Because the actual generation action uses a configurable Music Generator cost with a 100-Token source fallback, check Monthly Tokens before starting substantial music-generation sessions.
If one generation returns multiple versions, listen to all of them before generating again.
A second returned version may already provide the variation you need.
For a music track you intend to use externally:
Although My Creations is persistent, retaining an external authorized copy of important completed tracks gives you additional control over your business assets.
Music Generator creates media through an external generation provider.
The source bundle establishes the generation workflow but does not contain a subscriber-facing license agreement defining every commercial-use right associated with each generated track.
Before high-value commercial distribution, review the current applicable AIUNIFY/provider terms governing generated music.
If a song references:
review the Lyrics/content before using the track publicly.
Music generation is creative output, not fact verification.
Use original creative direction rather than instructing the system to improperly reproduce protected recordings or distinctive copyrighted songs.
For business music, specify:
rather than requiring a copied recording.
Check:
The page requires both authentication and FeatureGuard access.
The button remains disabled if:
If you receive:
Prompt Required
“Please enter a description or lyrics for your music.”
enter content in either:
depending on your selected mode.
Normal Mode has a verified:
500-character
maximum.
Shorten the description or switch to Custom only when the task is actually a Lyrics-based workflow.
Custom Mode has a verified:
5,000-character
maximum.
Reduce the Lyrics if that limit is reached.
If generation returns:
“Insufficient tokens. Please top up your balance.”
check:
Sidebar → Monthly Tokens.
Remember that the execution source uses the configured Music Generator cost or its 100-Token fallback—not the generic 20-Token catalogue value.
Music Studio polls the provider approximately every three seconds.
Allow the Task to continue.
The UI's 30–60 second message is an estimate rather than a strict timeout.
This does not necessarily mean the provider is exactly 70% complete.
The current visual implementation uses a state-based 30%/70% progress display.
Wait for the actual Status to become Success or Failed.
Read the message beneath:
Generation Failed.
Possible source-supported failure categories include:
If an error specifically refers to provider:
Credits insufficient
do not assume adding PROS SUITE Monthly Tokens alone will necessarily solve it.
That wording can originate from the external generation provider.
That is the current verified implementation.
The Download/Save controls open the audio URL in a new tab.
Use your browser's available audio/save controls if you need a local copy.
No format chooser is source-verified in the current Music Studio.
The application receives an audio URL rather than asking the user to choose an export format.
The current My Creations Card does not contain a Delete control.
Deletion is not established as an ordinary-user Music Studio action in the current source.
The current Music Studio does not expose Rename.
Use the Title field before generation to give future tracks an identifiable Name.
Try:
Refresh History.
Successful Music Tasks normally persist returned audio versions as the signed-in user's music assets.
The history action requires a valid signed-in session.
If the account cannot be identified, the service returns:
Unauthorized.
Confirm that your PROS SUITE session remains active.
If the isolation service returns an error, Music Studio displays:
Isolation Failed
and the specific message.
Check especially for insufficient audio-processing Tokens.
The exact current server error is:
“Insufficient tokens for audio processing.”
Audio Isolation has its own configurable cost separate from Music generation.
This is expected.
Music Studio has its own Suno Model selector and does not use the shared Header language Model for generation.
Choose between:
inside Music Studio itself.
MUSIC GENERATOR
↓
STUDIO
↓
NORMAL
↓
Music Description
↓
Style / Genre
↓
Optional:
Title
↓
Optional:
Instrumental Mode
↓
Select Suno Model
↓
GENERATE MUSIC
↓
QUEUING / GENERATING / PROCESSING
↓
MUSIC GENERATED
↓
PLAY ALL VERSIONS
↓
DOWNLOAD / SAVE
↓
Automatically available through:
MY CREATIONS
MUSIC GENERATOR
↓
STUDIO
↓
CUSTOM
↓
Enter Lyrics
↓
Style / Genre
↓
Title
↓
Choose:
Vocals / Instrumental Mode
↓
Suno Model
↓
GENERATE MUSIC
↓
REVIEW RESULTS
↓
SAVE DESIRED VERSION
GENERATED TRACK
or:
MY CREATIONS
↓
ISOLATE
↓
Check Audio-Isolation Token availability
↓
Starting Isolation
↓
ElevenLabs Processing Task
↓
Task Created
↓
Review the resulting isolation output when it becomes available through the applicable Music workflow.
Before generating:
After success:
You should now be able to:
The source verifies:
The current subscriber source does not establish:
Do not include these as active user operations unless a later source/UI release verifies them.
The three relevant cost concepts should remain separate:
Music Generator:
20 Tokens
Configured:
aiLimits['music-generator']
otherwise:
100 Tokens
Configured:
aiLimits['audio-isolation']
otherwise:
50 Tokens
For actual Music Generator operation, the direct server action is the stronger source than the generic feature catalogue.
The current workflow is:
AI MUSIC STUDIO
↓
Choose:
NORMAL
or:
CUSTOM
↓
Enter:
MUSIC DESCRIPTION
or:
LYRICS
↓
Optional:
STYLE / GENRE
TITLE
INSTRUMENTAL MODE
↓
Select:
SUNO V5
SUNO V4.5
or:
SUNO V4.5 PLUS
↓
GENERATE MUSIC
↓
QUEUING
↓
GENERATING / PROCESSING
↓
MUSIC GENERATED!
↓
GENERATED MASTERPIECES
↓
Choose:
PLAY
DOWNLOAD
ISOLATE
↓
Persisted in:
MY CREATIONS
AIUNIFY PROS SUITE Music Generator is a dedicated audio-generation workspace presented as:
AI Music Studio
with:
“Turn your ideas into professional-grade soundtracks with Suno V5.”
Subscribers can create music through two modes:
Normal → Music Description
and:
Custom → Lyrics.
Normal Mode permits up to 500 characters, while Custom Lyrics supports up to 5,000 characters. Users can additionally set:
The current Suno choices are:
These Models are specific to Music Generator and are separate from the shared PROS SUITE Header AI Model selector.
Selecting Generate Music creates an asynchronous provider Task. Music Studio then polls the Task approximately every three seconds and can display Queuing, Generating, Processing, Success, or Failed states.
Successful generation displays:
Music Generated!
“Your masterpiece is ready to listen.”
One request can produce multiple audio versions, and successful versions are persisted as account-specific Music assets so they can later appear under:
My Creations → Generation History.
Users can Play/Pause new and saved tracks. The current Download and Save controls open the provider audio URL in a new browser tab rather than constructing a named local download file.
Music Studio also provides Audio Isolation Pro, which sends a selected audio URL to an ElevenLabs audio-isolation workflow. The server uses a configurable audio-isolation Token cost with a current source fallback of 50 Tokens.
For Music generation itself, the direct execution source checks the configured music-generator cost and falls back to 100 Tokens. This conflicts with the generic feature catalogue's 20-Token entry, so the manual does not present 20 Tokens as the guaranteed live generation price.
The recommended operating method is:
Choose Normal or Custom → Define the Music Clearly → Add Style and Title → Choose Instrumental/Vocal Direction → Select the Suno Model → Check Monthly Tokens → Generate → Listen to Every Returned Version → Preserve the Best Track → Use My Creations for Future Access → Use Audio Isolation Only When Needed