yhaha/EmoVoice

EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting

Overview

EmoVoice is a emotion-controllable TTS model that exploits large language models (LLMs) to enable fine-grained freestyle natural language emotion control. EmoVoice achieves SOTA performance on English EmoVoice-DB and Chinese Secap test sets.

<!-- ## Environmental Setup

### Create a separate environment if needed

conda create -n EmoVoice python=3.10
conda activate EmoVoice
pip install -r requirements.txt

Train and Inference

Infer with checkpoints

bash examples/tts/scripts/inference_EmoVoice.sh
bash examples/tts/scripts/inference_EmoVoice-PP.sh
bash examples/tts/scripts/inference_EmoVoice_1.5B.sh

Train from scratch

# First Stage: Pretrain TTS
bash examples/tts/scripts/pretrain_EmoVoice.sh
bash examples/tts/scripts/pretrain_EmoVoice-PP.sh
bash examples/tts/scripts/pretrain_EmoVoice_1.5B.sh

# Second Stage: Finetune Emotional TTS
bash examples/tts/scripts/ft_EmoVoice.sh
bash examples/tts/scripts/ft_EmoVoice-PP.sh
bash examples/tts/scripts/ft_EmoVoice_1.5B.sh
``` -->

### Checkpoints
English model checkpoints of EmoVoice(0.5B), EmoVoice(1.5B) and EmoVoice-PP(0.5B) are uploaded.  
Qwen2.5-0.5B-phn, the Qwen2.5-0.5B tokenizer with a phoneme-extended vocabulary, is uploaded.

## Citation
If our work is useful for you, please cite as:

@article{yang2025emovoice, title={EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting}, author={Yang, Guanrou and Yang, Chen and Chen, Qian and Ma, Ziyang and Chen, Wenxi and Wang, Wen and Wang, Tianrui and Yang, Yifan and Niu, Zhikang and Liu, Wenrui and others}, journal={arXiv preprint arXiv:2504.12867}, year={2025} }