MMLForge Search models, datasets, tasks… Start free

Home › Models › Text To Speech › herimor/voxtream2

V

herimor/voxtream2

Text To Speech·herimor· 2.1K· 6

voxtream cc-by-4.0 Text To Speech 462.9M params dataset:amphion/Emilia-Datasetdataset:nvidia/hifitts-2arxiv:2603.13518arxiv:2509.15969license:cc-by-4.0

VoXtream2 is a zero-shot full-stream TTS model with dynamic speaking-rate control that can be updated mid-utterance on the fly. It was introduced in the paper VoXtream2: Full-stream TTS with dynamic speaking rate control.

Open in MLForge Sign up free Desktop app Source ↗

# pull & run locally
pip install mlforge-sdk && mlforge pull herimor/voxtream2

Model details

Task

Text To Speech

Provider

herimor

Framework

voxtream

Parameters

462.9M

Size

2.4 GB

License

cc-by-4.0

Downloads

2.1K

Likes

6

Paper

arXiv:2603.13518

Updated

2026-03-18

About herimor/voxtream2

VoXtream2 is a zero-shot full-stream TTS model with dynamic speaking-rate control that can be updated mid-utterance on the fly. It was introduced in the paper VoXtream2: Full-stream TTS with dynamic speaking rate control.

Related Text To Speech

K hexgrad/Kokoro-82M Text To Speech 15.5M 6.4K 🤗 HF X coqui/XTTS-v2 Text To Speech 9.2M 3.6K 🤗 HF C ResembleAI/chatterbox Text To Speech 2.2M 1.7K 🤗 HF Q Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice Text To Speech ·1.9B params 2.0M 1.6K 🤗 HF Q Qwen/Qwen3-TTS-12Hz-0.6B-CustomVoice Text To Speech ·905.8M params 1.2M 163 🤗 HF O k2-fsa/OmniVoice Text To Speech ·612.6M params 1.0M 1.1K 🤗 HF

Browse all Text To Speech models →