ACE-Step 1.5 is an AI music generation model available on Tunee. Multilingual flagship model with precise style control. It costs 9 credits per track and supports a maximum duration of 600 seconds per generation. Whether you're a professional creator or just getting started, ACE-Step 1.5 delivers consistent, high-quality results that meet the demands of modern content creation.
| Output Format | MP3, WAV |
| Max Duration | 600 seconds |
| Credits | 9 per track |
| Language Support | 10+ languages |
ACE-Step 1.5 is trained on an extensive multilingual vocal dataset, delivering natural-sounding singing in English, Chinese, Japanese, Korean, Spanish, French, and more with authentic phonetics and prosody.
A fine-grained style conditioning system allows detailed control over vocal character, singing technique, genre tropes, and production style — giving creators unprecedented creative precision.
With the longest maximum duration of any model on Tunee at 600 seconds, ACE-Step 1.5 is ideal for extended compositions, full-length songs, and long-form audio experiences.
Go to tunee.ai and sign in to your account — or create one free in seconds.
In the music or video creation screen, open the model selector and choose this model from the list.
Describe your creative vision, hit Generate, and download your track or video clip instantly.