---
title: voxtream
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/voxtream"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/voxtream.md"
repository: AI-ModelScope/voxtream
last_updated: 2026-10-13
license: cc-by-nc-4.0
pipeline_tag: text-to-speech
tasks:
  - text-to-speech
parameters: 441.8M
tensor_type:
  - F32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 103
stars: 0
tags:
  - voxtream
  - text-to-speech
---

# voxtream

> voxtream - AI-ModelScope 在 ModelScope 开源的模型。Model Card for VoXtream

AI-ModelScope/voxtream 是 ModelScope 魔搭社区上的 441.8M 参数text-to-speech模型，采用 cc-by-nc-4.0 许可。

- **Repository**: AI-ModelScope/voxtream
- **License**: cc-by-nc-4.0
- **Tasks**: text-to-speech
- **Parameters**: 441.8M
- **Tags**: voxtream, text-to-speech
- **Downloads**: 103
- **Stars**: 0
- **Last updated**: 2026-10-13

Source: https://www.modelscope.cn/models/AI-ModelScope/voxtream

---

# Model Card for VoXtream

VoXtream, a fully autoregressive, zero-shot streaming text-to-speech system for real-time use that begins speaking from the first word.

### Key features

- **Streaming**: Support a full-stream scenario, where the full sentence is not known in advance. The model takes the text stream coming word-by-word as input and outputs an audio stream in 80ms chunks.
- **Speed**: Works **5x** times faster than real-time and achieves **102 ms** first packet latency on GPU.
- **Quality and efficiency**: With only 9k hours of training data, it matches or surpasses the quality and intelligibility of larger models or models trained on large datasets.

### Model Sources 

- **Repository:** [repo](https://github.com/herimor/voxtream/tree/voxtream) 
- **Paper:** [paper](https://arxiv.org/pdf/2509.15969) 
- **Demo:** [demo](https://herimor.github.io/voxtream) 

## Get started

### Installation

```bash
pip install voxtream==0.1.5
```

### Usage

#### Output streaming
```bash
voxtream \
    --prompt-audio assets/audio/male.wav \
    --prompt-text "The liquor was first created as 'Brandy Milk', produced with milk, brandy and vanilla." \
    --text "In general, however, some method is then needed to evaluate each approximation." \
    --output "output_stream.wav"
```
* Note: Initial run may take some time to download model weights.

#### Full streaming
```bash
voxtream \
    --prompt-audio assets/audio/female.wav \
    --prompt-text "Betty Cooper helps Archie with cleaning a store room, when Reggie attacks her." \
    --text "Staff do not always do enough to prevent violence." \
    --output "full_stream.wav" \
    --full-stream
```

### Out-of-Scope Use

Any organization or individual is prohibited from using any technology mentioned in this paper to generate someone's speech without his/her consent, including but not limited to government leaders, political figures, and celebrities. If you do not comply with this item, you could be in violation of copyright laws.

## Training Data

The model was trained on a 9k-hour subset from [Emilia](https://huggingface.co/datasets/amphion/Emilia-Dataset) and [HiFiTTS2](https://huggingface.co/datasets/nvidia/hifitts-2) datasets. You can download it [here](https://huggingface.co/datasets/herimor/voxtream-train-9k). For more details, please check our paper. 

## Citation 

```
@inproceedings{torgashov2026voxtream,
  title={Vo{X}tream: Full-Stream Text-to-Speech with Extremely Low Latency},
  author={Torgashov, Nikita and Henter, Gustav Eje and Skantze, Gabriel},
  booktitle={Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  year={2026},
  note={to appear},
  url={https://arxiv.org/abs/2509.15969}
}
```