# TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis

arXiv: https://arxiv.org/abs/2505.14910 · HTML: https://mlsanity.com/paper/2505.14910/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 30 of 35)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Root Mean Square Layer Normalization](https://mlsanity.com/paper/1910.07467/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens](https://mlsanity.com/paper/2407.05407/) (2024)
- [Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron](https://mlsanity.com/paper/1803.09047/) (2018)
- [StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models](https://mlsanity.com/paper/2306.07691/) (2023)
- [Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus](https://mlsanity.com/paper/2112.10358/) (2021)
- [Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis](https://mlsanity.com/paper/2201.07429/) (2022)
- [MegaTTS 3: Sparse Alignment Enhanced Latent Diffusion Transformer for Zero-Shot Speech Synthesis](https://mlsanity.com/paper/2502.18924/) (2025)
- [VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis](https://mlsanity.com/paper/2110.08813/) (2021)
- [StyleTTS: A Style-Based Generative Model for Natural and Diverse Text-to-Speech Synthesis](https://mlsanity.com/paper/2205.15439/) (2022)
- [EvoMoE: An Evolutional Mixture-of-Experts Training Framework via Dense-To-Sparse Gate](https://mlsanity.com/paper/2112.14397/) (2021)
- [GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks](https://mlsanity.com/paper/2409.13832/) (2024)
- [Attentron: Few-Shot Text-to-Speech Utilizing Attention-Based Variable-Length Embedding](https://mlsanity.com/paper/2005.08484/) (2020)
- [StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis](https://mlsanity.com/paper/2312.10741/) (2023)
- [TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control](https://mlsanity.com/paper/2409.15977/) (2024)
- [TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching](https://mlsanity.com/paper/2502.12572/) (2025)
- [Scalable Geometric Fracture Assembly via Co-creation Space among Assemblers](https://mlsanity.com/paper/2312.12340/) (2023)
- [Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt](https://mlsanity.com/paper/2403.11780/) (2024)
- [Learning the Beauty in Songs: Neural Singing Voice Beautifier](https://mlsanity.com/paper/2202.13277/) (2022)
- [Robust Singing Voice Transcription Serves Synthesis](https://mlsanity.com/paper/2405.09940/) (2024)
- [A Melody-Unsupervision Model for Singing Voice Synthesis](https://mlsanity.com/paper/2110.06546/) (2021)
- [MuSE-SVS: Multi-Singer Emotional Singing Voice Synthesizer that Controls Emotional Intensity](https://mlsanity.com/paper/2203.00931/) (2022)
- [ISDrama: Immersive Spatial Drama Generation through Multimodal Prompting](https://mlsanity.com/paper/2504.20630/) (2025)

## Built on by (most cited first, 5 of 5)

- [RULER-Bench: Probing Rule-based Reasoning Abilities of Next-level Video Generation Models for Vision Foundation Intelligence](https://mlsanity.com/paper/2512.02622/) (2025)
- [YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidance](https://mlsanity.com/paper/2512.04779/) (2025)
- [Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion](https://mlsanity.com/paper/2507.14534/) (2025)
- [SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis](https://mlsanity.com/paper/2602.07803/) (2026)
- [VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models](https://mlsanity.com/paper/2605.04613/) (2026)

## Abstract (arXiv)

Customizable multilingual zero-shot singing voice synthesis (SVS) has various potential applications in music composition and short video dubbing. However, existing SVS models overly depend on phoneme and note boundary annotations, limiting their robustness in zero-shot scenarios and producing poor transitions between phonemes and notes. Moreover, they also lack effective multi-level style control via diverse prompts. To overcome these challenges, we introduce TCSinger 2, a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts. TCSinger 2 mainly includes three key modules: 1) Blurred Boundary Content (BBC) Encoder, predicts duration, extends content embedding, and applies masking to the boundaries to enable smooth transitions. 2) Custom Audio Encoder, uses contrastive learning to extract aligned representations from singing, speech, and textual prompts. 3) Flow-based Custom Transformer, leverages Cus-MOE, with F0 supervision, enhancing both the synthesis quality and style modeling of the generated singing voice. Experimental results show that TCSinger 2 outperforms baseline models in both subjective and objective metrics across multiple related tasks. Singing voice samples are available at https://aaronz345.github.io/TCSinger2Demo/.