Skip to content
Audio

OmniVoice

zero-shot TTS на 600+ языков

1 min readupdated

OmniVoice — массово многоязычная zero-shot TTS-модель на 0,61 млрд параметров, построенная на базе Qwen3-0.6B. Архитектура в стиле diffusion language model; поддерживает клонирование и дизайн голоса.

Ключевые особенности

  • 600+ языков — по заявлению авторов, самая широкая поддержка среди zero-shot TTS-моделей.
  • Zero-shot клонирование голоса по короткому референсному аудио.
  • Voice design: управление полом, возрастом, высотой тона, диалектом/акцентом, шёпотом и др.
  • Быстрый инференс: RTF до 0,025 — до 40× быстрее реального времени.
  • Тонкий контроль: невербальные символы вроде [laughter] и коррекция произношения через пиньинь или фонемы.
  • Diffusion language model-style архитектура на базе Qwen3-0.6B.

Пример

from omnivoice import OmniVoice
import soundfile as sf
import torch

model = OmniVoice.from_pretrained('k2-fsa/OmniVoice', device_map='cuda:0', dtype=torch.float16)
audio = model.generate(text='Hello, this is a test.', ref_audio='ref.wav', ref_text='Transcription.')
sf.write('out.wav', audio[0], 24000)
ПодробнееRTF до 0,025 — примерно 40× быстрее реального времени.
Аудио на выходе — 24 кГц.
Код — Apache 2.0, веса — CC-BY-NC из-за ограничений обучающих данных (например, Emilia).
Запрещено несанкционированное клонирование голоса и имперсонация.
Discuss Telegram 1

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # Infinix-io/OmniVoice
    # ===== Tokens: paste yours between the quotes =====
    export HF_TOKEN=""        # huggingface.co/settings/tokens, for gated models
    # ==========================================
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download Infinix-io/OmniVoice --local-dir ~/models/OmniVoice
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to OmniVoice
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

New posts about versions of OmniVoice (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

Infinix-io/OmniVoice
Author
Infinix-io
Category
Audio
Released
Posted

On NeyroLearn

Hugging Face

01

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments

Computer vision

Reviso

Reviso