SongGeneration-v2
The facts below are what the maker publishes about SongGeneration-v2, checked and dated. Our editors have not written about it yet.
The facts
Each one read from SongGeneration-v2's own pages, with the date it was checked.
What it does
- Audio upload
- Yeschecked 22 Sep 2026
- Commercial use
- Nochecked 22 Sep 2026
- Compute requirements
- The v2-large model listing specifies 22G GPU memory without prompt audio and 28G with prompt audio.checked 12 Oct 2026
- Generation controls
- Generation can be guided by lyrics, text tags for musical attributes, and an optional audio prompt.checked 12 Oct 2026
- Input constraints
- The maker says lyrics require structured section labels and specific punctuation, and recommends comma-separated tags rather than full sentences for descriptions.checked 12 Oct 2026
- Installation
- The README gives a local installation path requiring Python 3.8.12 or newer and CUDA 11.8 or newer, and also documents a Docker option.checked 12 Oct 2026
- Languages
- The listed SongGeneration-v2-large model supports Chinese, English, Spanish, Japanese, and other languages.checked 11 Oct 2026
- Languages and duration
- The v2-large model is listed for Chinese, English, Spanish, Japanese, and other languages, with a maximum song length of 4 minutes 30 seconds.checked 12 Oct 2026
- Local setup
- The repository instructions require Python 3.8.12 or newer and CUDA 11.8 or newer, and also describe running the project with Docker.checked 11 Oct 2026
- Model limits
- SongGeneration-v2-large supports songs up to 4 minutes 30 seconds and lists GPU memory requirements of 22G without prompt audio or 28G with it.checked 11 Oct 2026
- Model size
- The maker says SongGeneration-v2-large has 4 billion parameters.checked 12 Oct 2026
- Output modes
- The model can generate songs with vocals and accompaniment, pure music, vocal-only audio, or separate vocal and accompaniment tracks.checked 12 Oct 2026
- Outputs
- It can generate songs with vocals and accompaniment, pure music, vocal-only audio, or separate vocal and accompaniment tracks.checked 11 Oct 2026
- Product
- SongGeneration 2, also called LeVo 2, is an open-source music foundation model for AI music generation.checked 11 Oct 2026
- Prompt audio limit
- For audio prompts longer than 10 seconds, only the first 10 seconds are used.checked 12 Oct 2026
- Prompt controls
- Text descriptions can specify gender, genre, emotion, and instruments; an audio prompt uses its first 10 seconds.checked 11 Oct 2026
- Prompt limitation
- The README advises against combining audio prompts and text descriptions when their instructions conflict because generation quality may degrade.checked 11 Oct 2026
- Purpose
- LeVo 2 (SongGeneration 2) is described as an open-source music foundation model for generating songs.checked 12 Oct 2026
- Quality caveat
- The maker says conflicting information in a text description and audio prompt can reduce generation quality, and that prompt choice can affect performance.checked 12 Oct 2026
- Security
- The README does not state security or compliance certifications or practices.checked 12 Oct 2026
- Security and compliance
- The repository page does not state security certifications or compliance claims.checked 11 Oct 2026
- Song generation
- It generates songs from lyrics and can use text descriptions or audio prompts to guide the music.checked 11 Oct 2026
- Stem export
- Yeschecked 22 Sep 2026
Money
- Free plan
- Yeschecked 22 Sep 2026
Alternatives to SongGeneration-v2
- 1
Loudly
Free planAndroidiOSWebAPI9.1From $96 a year - 2
Suno
Free planAndroidiOS8.8From $8 a month - 3
Melody Genie
Free planAndroidiOSWebAPI8.7From $7.99 a month - 4
Song.do
Free planAndroidiOSWeb8.7From $10 a month - 5
MakeBestMusic
Free planAndroidiOSWebAPI8.7From $14.90 a month - 6
Treblo
Free planAndroidiOSWebAPI8.6Free plan