---
license: cc-by-nc-4.0
pipeline_tag: text-to-speech
tags:
- tts
- speech-synthesis
- emotion-control
---

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

EmoVoice is a novel emotion-controllable Text-to-Speech (TTS) model that exploits large language models (LLMs) to enable fine-grained freestyle natural language emotion control, and a phoneme boost variant design to enhance content consistency.

This model was presented in the paper: [EmoVoice: LLM-based Emotional Text-To-Speech Model with Freestyle Text Prompting](https://huggingface.co/papers/2504.12867).

For more details, check out the [project page](https://yanghaha0908.github.io/EmoVoice/) and the [GitHub repository](https://github.com/yanghaha0908/EmoVoice).

## Installation

### Create a separate environment if needed

```bash
conda create -n EmoVoice python=3.10
conda activate EmoVoice
pip install -r requirements.txt
```
## Usage

### Decode with checkpoints
```bash
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
```bash
# Fisrt 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
- Checkpoints can be found on Hugging Face: https://huggingface.co/yhaha/EmoVoice

## Dataset

- Pretrain TTS: [VoiceAssistant](https://huggingface.co/datasets/worstchan/VoiceAssistant-400K-SLAM-Omni)
- Finetune Emotional TTS: [EmoVoice-DB](https://huggingface.co/datasets/yhaha/EmoVoice-DB) and part of [laions_got_talent](https://huggingface.co/datasets/laion/laions_got_talent)

## Acknowledgements
- Our codes is built on [SLAM-LLM](https://github.com/X-LANCE/SLAM-LLM)
- [CosyVoice](https://github.com/FunAudioLLM/CosyVoice) valuable repo

## Citation

If our work and codebase 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}
}
```