# Vocal Synth Models

## Model Generation Evolution

ACE Studio continuously iterates its vocal synthesis models. Building on state-of-the-art AI architectures, we incorporate proprietary innovations to enhance naturalness, expressiveness, multilingual accuracy, and voice cloning fidelity. 

We also responsibly expand our vocal datasets to cover more languages and musical styles. When architectural improvements and new training data meet our release criteria, we publish a new model generation.

<figure><img src="https://3596338706-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fsn71WYzecYYQw3KkF40b%2Fuploads%2FEBy73fsiyTV8fJrPnR3x%2Fmodel_list.gif?alt=media&#x26;token=c51015f5-12fa-4841-83b5-082059fdc2a4" alt="Select Vocal Synth Models in ACE Studio."><figcaption></figcaption></figure>

## Model List

Below is the current lineup of model generations and variants:

<table><thead><tr><th width="143.20703125">Model Name</th><th>Description</th><th>Language Support</th></tr></thead><tbody><tr><td><img src="https://3596338706-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fsn71WYzecYYQw3KkF40b%2Fuploads%2Fg5EoBOfbW45GLswOg41i%2Fverse25.png?alt=media&#x26;token=dc491f08-08c3-47a3-9235-da21c7e190ae" alt="" data-size="line"> Verse25</td><td>Advanced vocal synth model with high performance and quality.</td><td>English, Spanish, Italian, French, Portuguese, Korean, Chinese, Japanese</td></tr><tr><td>Verse24</td><td>A vocal synth model enhanced with English and Spanish capabilities.</td><td>English, Spanish, Chinese, Japanese</td></tr><tr><td>Solo24</td><td>A vocal synth model expanded from Verse24, designed for voice cloning.</td><td>English, Chinese, Japanese</td></tr><tr><td>Verse23B</td><td>Enhanced based on the Verse23 model.</td><td>English, Chinese, Japanese</td></tr><tr><td>SoloD</td><td>A vocal synth model expanded from Verse23, designed for voice cloning.</td><td>English, Chinese, Japanese</td></tr><tr><td>Solo23</td><td>A vocal synth model expanded from Verse23, designed for voice cloning.</td><td>English, Chinese, Japanese</td></tr><tr><td>Verse23</td><td>ACE Studio's first multilingual vocal synth model.</td><td>English, Chinese, Japanese</td></tr></tbody></table>