| --- |
| language: |
| - en |
| - zh |
| pipeline_tag: text-to-audio |
| library_name: tencent-song-generation |
| --- |
| |
| # SongGeneration |
|
|
| <p align="center"><img src="img/logo.jpg" width="40%"></p> |
| <p align="center"> |
| <a href="https://levo-demo.github.io/">Demo</a> | <a href="https://arxiv.org/abs/2506.07520">Paper</a> | <a href="https://github.com/tencent-ailab/songgeneration">Code</a> | <a href="https://huggingface.co/spaces/tencent/SongGeneration">Space Demo</a> |
| </p> |
| |
|
|
| This repository is the official weight repository for LeVo: High-Quality Song Generation with Multi-Preference Alignment. In this repository, we provide the SongGeneration model, inference scripts, and the checkpoint that has been trained on the Million Song Dataset. |
|
|
| ## Model Versions |
|
|
| | Model | Max Length | Language | GPU Memory | RTF(H20) | Download Link | |
| | ------------------------ | :--------: | :------------------: | :--------: | :------: | ------------------------------------------------------------ | |
| | SongGeneration-base | 2m30s | zh | 10G/16G | 0.67 | [Huggingface](https://huggingface.co/tencent/SongGeneration/tree/main/ckpt/songgeneration_base) | |
| | SongGeneration-base-new | 2m30s | zh, en | 10G/16G | 0.67 | [Huggingface](https://huggingface.co/lglg666/SongGeneration-base-new) | |
| | SongGeneration-base-full | 4m30s | zh, en | 12G/18G | 0.69 | [Huggingface](https://huggingface.co/lglg666/SongGeneration-base-full) | |
| | SongGeneration-large | 4m30s | zh, en | 22G/28G | 0.82 | [Huggingface](https://huggingface.co/lglg666/SongGeneration-large) | |
| | SongGeneration-v2-large | 4m30s | zh, en, es, ja, etc. | 22G/28G | 0.82 | [Huggingface](https://huggingface.co/lglg666/SongGeneration-v2-large) | |
| | SongGeneration-v2-medium | 4m30s | zh, en, es, ja, etc. | 12G/18G | 0.69 | Coming soon | |
| | SongGeneration-v2-fast | 4m30s | zh, en, es, ja, etc. | - | - | Coming soon | | |
|
|
| ## Overview |
|
|
| 🚀 We introduce LeVo 2 (SongGeneration 2), an open-source music foundation model designed to shatter the ceiling of open-source AI music by achieving true commercial-grade generation. |
|
|
| Through a large-scale, rigorous expert evaluation (20 industry professionals, 6 core dimensions, 100 songs per model), LeVo 2 has proven its superiority: |
|
|
| - 🏆 Commercial-Grade Musicality: Comprehensively outperforms all open-source baselines across Overall Quality, Melody, Arrangement, Sound Quality, and Structure. Its subjective generation quality successfully rivals top-tier closed-source commercial systems (e.g., MiniMax 2.5). |
| - 🎯 Precise Lyric Accuracy: Achieves an outstanding Phoneme Error Rate (PER) of 8.55%, effectively solving the lyrical hallucination problem. This remarkable accuracy significantly outperforms top commercial models like Suno v5 (12.4%) and Mureka v8 (9.96%). |
| - 🎛️ Exceptional Controllability: Highly responsive to multi-modal instructions, including text descriptions and audio prompts, allowing for precise control over the generated music. |
|
|
| 📊 *For detailed experimental setups and comprehensive metrics, please refer to the [Evaluation Performance](#Evaluation-Performance) section below or our upcoming technical report.* |
|
|
| <img src="img/output.png" alt="img" style="zoom:100%;" /> |
|
|
| ## License |
|
|
| The code and weights in this repository is released in the [LICENSE](LICENSE) file. |
|
|
