Instructions to use herimor/voxtream2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use herimor/voxtream2.5 with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf herimor/voxtream2.5:Q8_0 # Run inference directly in the terminal: llama cli -hf herimor/voxtream2.5:Q8_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf herimor/voxtream2.5:Q8_0 # Run inference directly in the terminal: llama cli -hf herimor/voxtream2.5:Q8_0
Build from source code
git clone https://github.com/ggml-org/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-app # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama serve -hf herimor/voxtream2.5:Q8_0 # Run inference directly in the terminal: ./build/bin/llama cli -hf herimor/voxtream2.5:Q8_0
Use Docker
docker model run hf.co/herimor/voxtream2.5:Q8_0
- Llama new
- LM Studio
- Jan
- Ollama
How to use herimor/voxtream2.5 with Ollama:
ollama run hf.co/herimor/voxtream2.5:Q8_0
- Unsloth Desktop
- Docker Model Runner
How to use herimor/voxtream2.5 with Docker Model Runner:
docker model run hf.co/herimor/voxtream2.5:Q8_0
- Lemonade
How to use herimor/voxtream2.5 with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull herimor/voxtream2.5:Q8_0
Run and chat with the model
lemonade run user.voxtream2.5-Q8_0
List all available models
lemonade list
- Atomic Chat
|
Download README.md from herimor/voxtream2.5: direct link, hf CLI and curl.
- Browser
- Download file 4.31 kB
-
https://huggingface.co/herimor/voxtream2.5/resolve/main/README.md
- Command line
-
hf download hf://herimor/voxtream2.5/README.md
-
curl -L -o README.md https://huggingface.co/herimor/voxtream2.5/resolve/main/README.md
4.31 kB
| 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} | |
| } | |
| ``` | |