OmniVoice
k2-fsa · OmniVoice
A zero-shot voice-cloning model from the k2-fsa (Next-gen Kaldi) team with the broadest language coverage of any open TTS model — 600+ languages from a single checkpoint. The code is Apache 2.0, but the pretrained weights are CC BY-NC because of constraints in the Emilia training data, so the released checkpoint is not free for commercial use without separate authorization.
Params
0.6B
License
Apache 2.0 (code) / CC BY-NC (pretrained weights)
Min VRAM
Not published — tested on server-class GPUs; also runs on Apple Silicon (MPS) and Intel Arc (XPU)
Languages
600+ languages (broadest coverage of any zero-shot TTS model)
Tier
Light
Install & run locally
pip install torch==2.8.0+cu128 torchaudio==2.8.0+cu128 --extra-index-url https://download.pytorch.org/whl/cu128
pip install omnivoice
from omnivoice import OmniVoice
model = OmniVoice.from_pretrained("k2-fsa/OmniVoice", device_map="cuda:0")
audio = model.generate(text="Hello, this is a test.", ref_audio="ref.wav")Full install and usage docs on the Hugging Face model card.
Will it run on my hardware?
OmniVoice needs about Not published — tested on server-class GPUs; also runs on Apple Silicon (MPS) and Intel Arc (XPU) of fast memory. Here is what in our hardware database clears that bar.
Memory requirement for this model is variable — see the run command and the model notes above.
Hardware links are affiliate links. We earn a small commission if you buy through them — at no extra cost to you. Disclosure
Specifications
| Parameters | 0.6B |
|---|---|
| License | Apache 2.0 (code) / CC BY-NC (pretrained weights) |
| Min VRAM | Not published — tested on server-class GPUs; also runs on Apple Silicon (MPS) and Intel Arc (XPU) |
| Languages | 600+ languages (broadest coverage of any zero-shot TTS model) |
| Recommended tier | Light |
| Best for | zero-shot voice cloningmultilingual speechlow-resource languages |
Source
Not distributed through Ollama — install and run it directly from the model card.
View on Hugging FacePopularity trend (illustrative)
Illustrative adoption trend, not actual download counts. We do not publish a download number for any model because we have no honest source for it.
Similar models
Kokoro-82M
hexgrad · Apache 2.0
The most-downloaded text-to-speech model on HuggingFace by a wide margin, at 11.6M downloads a month. At just 82M parameters it is small enough to run on CPU alone — no GPU minimum is published, unlike most other speech models here. Apache 2.0 licensed, so it is fully free for commercial use with no restrictions. Ships with 8 languages and 54 voices out of the box.
Min VRAM
None published — small enough to run on CPU alone
Speed
—
Install & run
pip install -q kokoro>=0.9.2 soundfileFish Audio S2 Pro
Fish Audio · Fish Audio Research License (non-commercial)
Fish Audio's flagship speech model, trained on 10M+ hours of audio with fine-grained inline control over prosody and emotion across 80+ languages. Needs a 24 GB GPU for CUDA inference, though a CPU-only install path exists for testing. Free for research and non-commercial use under the Fish Audio Research License; commercial use requires a separate paid license.
Min VRAM
24 GB GPU (CUDA) — CPU-only install also available
Speed
Real-time factor 0.195 on a single H200 · time to first audio ~100ms
Install & run
git clone https://github.com/fishaudio/fish-speech.gitQwen3-TTS 1.7B CustomVoice
Alibaba · Apache 2.0
Alibaba's Qwen3-TTS with 9 premium preset voices and instruction-based control over tone, emotion and prosody across 10 major languages. Streaming generation gets end-to-end latency as low as 97ms. Apache 2.0 licensed — fully free for commercial use, unlike most other speech models on this page.
Min VRAM
Not published — FlashAttention recommended to reduce memory use
Speed
End-to-end synthesis latency as low as 97ms (streaming)
Install & run
pip install -U qwen-tts