aufklarer / OmniVoice-MLX-int8

huggingface.co
Total runs: 43
24-hour runs: 0
7-day runs: -6
30-day runs: -17
Model's Last Updated: June 25 2026
text-to-speech

Introduction of OmniVoice-MLX-int8

Model Details of OmniVoice-MLX-int8

OmniVoice-MLX-int8

8-bit quantized MLX conversion of k2-fsa/OmniVoice — a single-stage, non-autoregressive discrete-diffusion text-to-speech model with a Qwen3 backbone and broad multilingual coverage (600+ languages). For Apple Silicon, via the speech-swift runtime.

Contents
File Precision Size
model.safetensors int8 backbone (group 64, 8-bit) ~689 MB
audio_tokenizer/model.safetensors fp16 codec (Higgs-audio v2) ~403 MB
tokenizer.json , config.json , … — —

The diffusion backbone is quantized (it dominates latency — 32 forward passes per clip); the codec stays fp16 since it runs once and is already exact there.

Why int8

The backbone is memory-bandwidth bound at these sequence lengths, so 8-bit weights cut latency with no audible loss. On an M5 Pro: RTF ≈ 0.18 (≈ 5.5× faster than real-time), versus ≈ 0.25 at fp32, and the ASR roundtrip stays at 0% WER .

Precision tiers:

Variant Backbone Total Use
OmniVoice-MLX-fp16 fp16 ~1.5 GB balanced
OmniVoice-MLX-int8 int8 ~1.0 GB fastest / smallest
Usage

Loaded by the OmniVoiceTTS module in speech-swift . The quantization block in config.json ( group_size: 64 , bits: 8 ) tells the loader to swap the Linear/Embedding layers to their quantized form before loading the weights.

License

Apache-2.0, following the upstream model.

Runs of aufklarer OmniVoice-MLX-int8 on huggingface.co

43
Total runs
0
24-hour runs
3
3-day runs
-6
7-day runs
-17
30-day runs

More Information About OmniVoice-MLX-int8 huggingface.co Model

More OmniVoice-MLX-int8 license Visit here:

https://choosealicense.com/licenses/apache-2.0

OmniVoice-MLX-int8 huggingface.co

OmniVoice-MLX-int8 huggingface.co is an AI model on huggingface.co that provides OmniVoice-MLX-int8's model effect (), which can be used instantly with this aufklarer OmniVoice-MLX-int8 model. huggingface.co supports a free trial of the OmniVoice-MLX-int8 model, and also provides paid use of the OmniVoice-MLX-int8. Support call OmniVoice-MLX-int8 model through api, including Node.js, Python, http.

OmniVoice-MLX-int8 huggingface.co Url

https://huggingface.co/aufklarer/OmniVoice-MLX-int8

aufklarer OmniVoice-MLX-int8 online free

OmniVoice-MLX-int8 huggingface.co is an online trial and call api platform, which integrates OmniVoice-MLX-int8's modeling effects, including api services, and provides a free online trial of OmniVoice-MLX-int8, you can try OmniVoice-MLX-int8 online for free by clicking the link below.

aufklarer OmniVoice-MLX-int8 online free url in huggingface.co:

https://huggingface.co/aufklarer/OmniVoice-MLX-int8

OmniVoice-MLX-int8 install

OmniVoice-MLX-int8 is an open source model from GitHub that offers a free installation service, and any user can find OmniVoice-MLX-int8 on GitHub to install. At the same time, huggingface.co provides the effect of OmniVoice-MLX-int8 install, users can directly use OmniVoice-MLX-int8 installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

OmniVoice-MLX-int8 install url in huggingface.co:

https://huggingface.co/aufklarer/OmniVoice-MLX-int8

Url of OmniVoice-MLX-int8

OmniVoice-MLX-int8 huggingface.co Url

Provider of OmniVoice-MLX-int8 huggingface.co

aufklarer
ORGANIZATIONS

Other API from aufklarer

huggingface.co

Total runs: 2.5K
Run Growth: 2.3K
Growth Rate: 94.66%
Updated:September 16 2025
huggingface.co

Total runs: 151
Run Growth: 93
Growth Rate: 61.59%
Updated:October 15 2025