Introduction
The following guide is a user-created usage manual shared by our Discord community. We’re reposting it here to help more users better understand Tunee’s system behavior and create more satisfying music with clearer guidance.
If you notice any areas that could be improved or have additional suggestions, feel free to reach out to our community moderators or supporters, or contact us directly at support@tunee.ai — we’re always happy to listen.
The full version of this guide can be found here:
View the complete guide on Notion
Tunee currently supports multiple core music generation models, each with a distinct sound character and ideal use case. Choosing the right model can significantly improve your results 
Model Sound Profile Overview
Here’s a quick breakdown to help you pick the best model for your workflow:
Mureka 7.6
- Cinematic tone with strong sense of space and layered harmonies
- Best for: Ambient music, film scoring, atmospheric electronic, soundscapes
Mureka O2
- Brighter, more modern sound with focused low-end
- Best for: Pop, modern electronic, vocal-driven songs
MiniMax Music 2.0
- Extremely tight rhythm and punchy bass response
- Best for: Synth-pop, club music, EDM, electronic beats
Tempolor v4.5 Beta
- Natural listening experience with rich reverb and smooth textures
- Best for: Dream pop, ambient R&B, emotional or mellow tracks
Language Support & Common Pitfalls
Tunee officially supports 10 languages for music generation:
Chinese, English, Japanese, Korean, Spanish, French, German, Italian, Portuguese, Russian
Requests for other languages or dialects are currently not supported and may be rejected.
Practical Notes from Testing
| Language | Best Models | Avoid Models | Known Quirks / Notes |
|---|---|---|---|
| Chinese (Mandarin) | Minimax Music 2.0 Mureka 7.6 | Tempolor v4.5 Beta | Excellent diction, expressive phrasing, and poetic rhythm. Works best with modern pop, R&B, and drama soundtracks. Avoid mixing Simplified and Traditional Chinese within the same lyric. |
| English | Minimax 2.0 | Tempolor v4.5 Beta (fast rap / dense lyrics) | Strong phoneme coverage and natural stress patterns. Suitable for almost all genres, especially pop-rock, ballads, and EDM. |
| Japanese | Mureka 7.6 | Minimax Music 2.0 | Handles mora timing and emotional nuance well. Ideal for city-pop, J-rock, and anime-style ballads. May struggle with Kansai dialect or heavy slang. |
| Korean | Mureka O2 Mureka 7.6 | Tempolor v4.5 Beta | Accurate spacing and Hangul syllable handling. K-pop and R&B perform best. Avoid deep regional dialects, especially Gyeongsang accent. |
| Spanish | Mureka 7.5 | Minimax Music 2.0 | Performs well for pop-Latin and reggaetón. Less suitable for poetic flamenco-style phrasing. |
| French | Mureka 7.5 | Minimax Music 2.0 | Elegant nasal vowel rendering. Chanson and synth-pop feel authentic. Dense wordplay may reduce clarity. |
| German | Mureka 7.5 | Tempolor v4.5 Beta | Handles consonant clusters cleanly. Works well for electronic and industrial genres; less natural for spoken-style hip-hop. |
Final Tip
If you’re not sure which model to use, start with the genre and language you need, then adjust based on vocal clarity and overall vibe. Small model changes can make a big difference 
If you have questions or run into issues, feel free to reach out — we’re always happy to help 