YuE2 generates songs from lyrics and a style prompt by creating an editable melody-and-chord plan, then rendering vocals and accompaniment. Users can alter harmony, melody, tempo, or form in an ABC score before generating a new recording. For covers, YuE2 can use a transcribed song melody to produce an interpretation in a target style. The hosted NOIZ browser demo accepts song descriptions and lyrics, while its cover studio accepts audio uploads up to 100 MB in formats including MP3, WAV, FLAC, M4A, AAC, and OGG. The listed free hosted demo is free and shows 3 generations left. Local setup specifies Linux, Python 3.12, and an NVIDIA GPU with BF16 support and 24 GB VRAM; output is 48 kHz stereo without quantization. A staged Python API exposes plan(), generate_semantic(), synthesize(), and decode(). Code, documentation, and the agent skill use Apache 2.0; model weights use CC BY-NC 4.0 with additional creator permission.
Who it is for
It suits musicians, content creators, and personal users who want editable song generation, covers, transcription, or score changes. Local users need the specified Linux, Python, and NVIDIA hardware setup; companies need model-weights licensing contact for commercial use.
What is good
- Editable melody-and-chord planning
- Generates vocals and accompaniment
- Supports cover creation from melodies
- Hosted browser demo available
- Python API and ComfyUI workflow linked
What to know first
- Local use requires Linux
- Local use requires 24 GB VRAM
- Hosted demo shows three generations left
- Commercial company use needs model licensing
Verdict
YuE2 combines lyric-driven song creation with editable scores, covers, a browser demo, and local or API workflows. Hardware requirements and model-weight licensing make the deployment choice important for users and companies.
YuE plans and pricing
All plansCompared on AI music generators
- Free plan
- Yes
- Commercial use
- Yes
- Vocal generation
- Yes
- Audio upload
- Yes
- Supported platforms
- web
