Freedom251 › AI Music Generators
SongGeneration-v2
What SongGeneration-v2 is
SongGeneration-v2, also called LeVo 2, is a free open-source music foundation model for generating songs. It accepts lyrics, comma-separated text tags, and optional audio prompts. Tags can describe gender, genre, emotion, and instruments, while an audio prompt uses only its first 10 seconds. The model can produce songs with vocals and accompaniment, instrumental music, vocal-only audio, or separate vocal and accompaniment tracks. The listed v2-large model supports Chinese, English, Spanish, Japanese, and other languages, with songs up to 4 minutes 30 seconds. The maker lists 4 billion parameters and GPU requirements of 22G without prompt audio or 28G with it. Local setup requires Python 3.8.12 or newer and CUDA 11.8 or newer, with Docker also documented. A Hugging Face web demo for SongGeneration-v2-Fast is described as generating a complete song in under one minute, with some musicality loss. It runs on Linux, self-hosted systems, and the web. Commercial use is not allowed.
Who it suits
It suits users who want open-source song generation from lyrics, musical tags, or audio prompts. It is intended for Linux, self-hosted, or web use, but not commercial projects.
What it does well
- Generates vocal, instrumental, and separated tracks
- Supports lyrics, text tags, and audio prompts
- Handles several listed languages
- Offers a web demo
- Free plan available
What to know first
- Commercial use is not allowed
- Requires up to 28G GPU memory
- Audio prompts use only ten seconds
- Lyrics require labeled sections and semicolons
Verdict
SongGeneration-v2 provides several generation inputs and output modes, including separated vocal and accompaniment tracks. Its hardware requirements, formatting rules, and non-commercial restriction are important constraints.
Facts from SongGeneration-v2's own pages
- Audio upload
- Yes · github.com, 22 Sept 2026
- Commercial use
- No · github.com, 22 Sept 2026
- Compute requirements
- The v2-large model listing specifies 22G GPU memory without prompt audio and 28G with prompt audio. · github.com, 12 Oct 2026
- Free plan
- Yes · github.com, 22 Sept 2026
- Generation controls
- Generation can be guided by lyrics, text tags for musical attributes, and an optional audio prompt. · github.com, 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. · github.com, 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. · github.com, 12 Oct 2026
- Languages
- The listed SongGeneration-v2-large model supports Chinese, English, Spanish, Japanese, and other languages. · github.com, 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. · github.com, 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. · github.com, 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. · github.com, 11 Oct 2026
- Model size
- The maker says SongGeneration-v2-large has 4 billion parameters. · github.com, 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. · github.com, 12 Oct 2026
- Outputs
- It can generate songs with vocals and accompaniment, pure music, vocal-only audio, or separate vocal and accompaniment tracks. · github.com, 11 Oct 2026
- Supported platforms
- web · github.com, 22 Sept 2026
- Product
- SongGeneration 2, also called LeVo 2, is an open-source music foundation model for AI music generation. · github.com, 11 Oct 2026
- Prompt audio limit
- For audio prompts longer than 10 seconds, only the first 10 seconds are used. · github.com, 12 Oct 2026
- Prompt controls
- Text descriptions can specify gender, genre, emotion, and instruments; an audio prompt uses its first 10 seconds. · github.com, 11 Oct 2026
- Prompt limitation
- The README advises against combining audio prompts and text descriptions when their instructions conflict because generation quality may degrade. · github.com, 11 Oct 2026
- Purpose
- LeVo 2 (SongGeneration 2) is described as an open-source music foundation model for generating songs. · github.com, 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. · github.com, 12 Oct 2026
- Security
- The README does not state security or compliance certifications or practices. · github.com, 12 Oct 2026
- Security and compliance
- The repository page does not state security certifications or compliance claims. · github.com, 11 Oct 2026
- Song generation
- It generates songs from lyrics and can use text descriptions or audio prompts to guide the music. · github.com, 11 Oct 2026
Where SongGeneration-v2 stands on Freedom251
- AI Music Generators#106 of 123