This is a complete walkthrough of the AI Music Generator on Oakgen.ai. Every feature, every setting, explained with screenshots.

Interface Overview

The Music Generator has two main areas:

• Left panel -- Your controls: music style description, lyrics input, model selector, and the Generate button.
• Right panel -- Your results: generated tracks, full tool history, and your saved library.

At the top of the right panel, you can switch between:

• Result Panel -- Shows your latest generation
• Music History -- Every track you have generated (with count)
• All -- All generations across all tools
• Library -- Tracks you have saved
• How it works -- A quick explainer of the generation process

Describing Your Music Style

The Music Style field is required. Describe the genre, mood, tempo, instruments, and vocal style you want. This field accepts 10 to 300 characters.

Good style descriptions include multiple attributes:

• "Upbeat pop, energetic, summer vibes, catchy melody, feel-good, radio-friendly"
• "Lo-fi hip-hop, chill beats, jazzy piano, vinyl crackle, late-night study mood"
• "Epic cinematic orchestral, dramatic strings, brass fanfare, trailer music"

Below the style field, Hints provide quick-start suggestions. Click Indie Folk or Upbeat Pop to populate the field instantly. Hit the refresh icon for new suggestions.

The sparkle icon (top-right of the style box) enhances your description with AI -- it expands a basic idea into a detailed, model-optimized style prompt.

Adding Lyrics (Optional)

The Lyrics field accepts up to 3,000 characters. You can write full song lyrics with section markers to structure the track:

[verse]
Pack your bags, leave it all behind
Adventure calling, break the grind
Mountain peaks and ocean waves
Freedom found in unknown caves

[chorus]
We are running wild and free
Every road is where we need to be

Supported section markers: [Intro], [Verse], [Chorus], [Bridge], [Outro]

If you leave the lyrics field empty:

• Some models will auto-generate lyrics based on your style description
• Some models will generate an instrumental track instead

Selecting an AI Model

Click Change next to the current model name to open the model selector. Oakgen offers 7 AI music models, each with different strengths.

All Available Models

| Model | Type | Vocals | Best For | Credits | |-------|------|--------|----------|---------| | Minimax Music V2 | Text-to-Music | Vocals + Lyrics | Full songs with vocals and structured lyrics. Supports section tags. High quality. | ~7 | | Minimax Music V1 | Text-to-Music | Vocals | Full songs with vocals. Previous-generation model. | ~7 | | Suno AI | Text-to-Music | Vocals | Feature-rich music generation. Multiple model versions (V4 to V5). Custom mode, instrumental toggle, vocal gender control, and negative tags. Generates 2 songs per request. | Varies | | Sonauto V2 | Text-to-Music | Flexible + Instrumental | Versatile model that auto-generates tags and lyrics from your prompt. Supports BPM control, multiple output formats (WAV, MP3, FLAC, OGG, M4A), and seed for reproducibility. | ~15 | | YuE | Lyrics-to-Music | Vocals | Open-source model that transforms structured lyrics into full songs. Requires section markers. Genre-guided style. | ~8 | | Lyria 2 | Text-to-Music | Instrumental | Google's state-of-the-art music generation. Best for instrumentals. Supports negative prompts and seed for reproducibility. | ~1 | | CassetteAI | Text-to-Music | Instrumental | Ultra-fast generation -- 30 seconds of music in ~2 seconds. Professional 44.1kHz stereo. Duration control from 10 to 180 seconds. Best for background music and instrumentals. | ~1 | | Eleven Music | Text-to-Music | Instrumental | ElevenLabs-powered instrumental generation. | ~1 |

Choosing the Right Model

Want vocals with lyrics? Use Minimax Music V2, Suno AI, or YuE.

Want instrumentals only? Use Lyria 2, CassetteAI, or Eleven Music.

Want the most control? Use Suno AI (custom mode, vocal gender, negative tags, style weight) or Sonauto V2 (BPM, output format, seed).

Want the fastest generation? Use CassetteAI -- it generates a 30-second track in about 2 seconds.

Want the cheapest option? Lyria 2, CassetteAI, and Eleven Music cost around 1 credit per generation.

Suno AI Model Versions

Suno AI offers multiple model versions, each with different capabilities:

| Version | Highlights | Max Duration | |---------|-----------|--------------| | V5 | Recommended. Superior expression and musicality. | 8 min | | V4.5+ | Richer sound, improved audio quality. | 8 min | | V4.5 All | Better song structure and arrangement. | 8 min | | V4.5 | Superior genre blending and style fusion. | 8 min | | V4 | Best raw audio quality, proven reliability. | 4 min |

Generating and Viewing Results

Click Generate Music to start. The button shows the credit cost (e.g., 7 credits for Minimax Music V2).

Once your track is ready, it appears in the Result Panel on the right. You can:

• Play the track directly in the browser using the green play button
• See the waveform visualization of the generated audio
• View the model used (e.g., Minimax Music V2) and the generation date
• Check Music History to see all past generations
• Download the track in full quality

You will also receive a real-time notification when the track is complete, so you do not need to stay on the page.

Quick Reference

| Feature | Where to Find It | |---------|-----------------| | Describe music style | Music Style text area (required, 10-300 chars) | | Add lyrics | Lyrics text area (optional, up to 3,000 chars) | | Enhance style with AI | Sparkle icon (top-right of style box) | | Change AI model | Click "Change" at bottom of left panel | | Browse all 7 models | Model selector modal | | View past generations | Music History tab (right panel) | | Save a track | Library tab (right panel) | | Learn how it works | "How it works" button (top-right of right panel) |