---
datasets:
- amphion/Emilia-Dataset
- nvidia/hifitts-2
language:
- en
license: cc-by-nc-4.0
pipeline_tag: text-to-speech
library_name: voxtream
tags:
- text-to-speech
- zero-shot
- streaming
- gguf
---

# Model Card for VoXtream2.5

VoXtream2.5 is a zero-shot full-stream TTS model with dynamic speaking-rate control that can be updated mid-utterance on the fly. It builds on VoXtream2, introduced in the paper [VoXtream2: Full-stream TTS with dynamic speaking rate control](https://huggingface.co/papers/2603.13518), with:

- **Hybrid depth transformer head**: 32 Mimi codebooks are generated in 4 steps (3 AR and a single Mixture of Gaussians step), which makes the model run ~10x faster than real-time on an RTX 3090.

- **CPU inference**: GGUF (int8) model runs in real-time on a single CPU core on llama.cpp.

- **Long-form generation**: Generation runs for up to 5 minutes with a WER below 2% measured on the LibriSpeech-long benchmark.

**Developed by:** Nikita Torgashov, Gustav Eje Henter, Gabriel Skantze

### Model Sources 

- **Repository:** [https://github.com/herimor/voxtream](https://github.com/herimor/voxtream)
- **Blogpost:** [https://herimor.github.io/voxtream2.5](https://herimor.github.io/voxtream2.5)
- **Live Demo:** [https://huggingface.co/spaces/herimor/voxtream2.5](https://huggingface.co/spaces/herimor/voxtream2.5)

### Files

- `model.safetensors`, `config.json`: the model weights and config.
- `phoneme_vocab.json`: the phoneme vocabulary the training data was built with.
- `*-q8_0.gguf`, `voxtream_gguf.json`: the temporal transformer, depth transformer, MoG head and Mimi decoder transformer for llama.cpp.

## Get started

### Installation

### eSpeak NG phonemizer

```bash
# For Debian-like distribution (e.g. Ubuntu, Mint, etc.)
apt-get install espeak-ng
# For RedHat-like distribution (e.g. CentOS, Fedora, etc.) 
yum install espeak-ng
# For MacOS
brew install espeak-ng
```

### Pip package

```bash
pip install "voxtream>=0.2.6"
```

### Usage

* Prompt audio: a file containing 3-10 seconds of the target voice. The maximum supported length is 20 seconds (longer audio will be trimmed).
* Text: What you want the model to say.
* Speaking rate (optional): target speaking rate in syllables per second.

#### Output streaming
```bash
voxtream \
    --prompt-audio assets/audio/english_male.wav \
    --text "In general, however, some method is then needed to evaluate each approximation." \
    --output "output_stream.wav"
```

#### Full streaming (slow speech, 2 syllables per second)
```bash
voxtream \
    --prompt-audio assets/audio/english_female.wav \
    --text "Staff do not always do enough to prevent violence." \
    --output "full_stream_2sps.wav" \
    --full-stream \
    --spk-rate 2.0
```

#### CPU inference with llama.cpp (int8)
```bash
voxtream \
    --prompt-audio assets/audio/english_male.wav \
    --text "In general, however, some method is then needed to evaluate each approximation." \
    --output "output_cpu.wav" \
    --threads 2
```

* Note: Initial run may take some time to download model weights and warmup model graph.

## Training Data

The model was trained on [Emilia](https://huggingface.co/datasets/amphion/Emilia-Dataset) and [HiFiTTS2](https://huggingface.co/datasets/nvidia/hifitts-2) datasets. For more details, please check our paper.

### 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.

## Citation 

```bibtex
@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}
}

@article{torgashov2026voxtream2,
  author    = {Torgashov, Nikita and Henter, Gustav Eje and Skantze, Gabriel},
  title     = {Vo{X}tream2: Full-stream TTS with dynamic speaking rate control},
  journal   = {arXiv:2603.13518},
  year      = {2026}
}
```