Models
MODELHugging Face
5/5

OmniVoice / TTS-Multi_language_High_Quality

Algerian Saharan Arabic(aao)TTS / zero-shot multilingual text-to-speech; diffusion language model-style discrete NAR architectureOmniVoice 0.8BOmniVoice
View Source

Model Info

Language
Algerian Saharan Arabic (aao)
Architecture
OmniVoice
Institution
Han Zhu, Lingxuan Ye, Wei Kang, Zengwei Yao, Liyong Guo, Fangjun Kuang, Zhifeng Han, Weiji Zhuang, Long Lin, Daniel Povey
Last Updated
11 May 2026

Intended Use Cases

Multilingual TTS; zero-shot TTS; voice cloning / voice design

License & Access

SPDX identifierapache-2.0

Open — attribution required; commercial use allowed.

Provenance

Source URL
https://huggingface.co/hik63382/TTS-Multi_language_High_Quality
Fetch Timestamp
11 May 2026
Submitter
Han Zhu, Lingxuan Ye, Wei Kang, Zengwei Yao, Liyong Guo, Fangjun Kuang, Zhifeng Han, Weiji Zhuang, Long Lin, Daniel Povey

Full Record

20 of 25 fields stated

Every column the registry tracks. Values marked derivedwere filled by a rule or read from the source's text rather than stated in its metadata; the rule or the quoted sentence is shown under the value.

Registry columns (16/18)

iso code
aao
Model Name
OmniVoice / TTS-Multi_language_High_Quality
Where is it hosted
HuggingFace / GitHub
Link
https://huggingface.co/hik63382/TTS-Multi_language_High_Quality
Year
Not stated
Creator/Author(s)
Han Zhu, Lingxuan Ye, Wei Kang, Zengwei Yao, Liyong Guo, Fangjun Kuang, Zhifeng Han, Weiji Zhuang, Long Lin, Daniel Povey
Paper Reference
https://arxiv.org/abs/2604.00688
NLP Task
TTS / zero-shot multilingual text-to-speech; diffusion language model-style discrete NAR architecture
Architecture
OmniVoicederivedHugging Face config: architectures / model_type
Base Model
OmniVoice 0.8B
Fine-tuned?
No
License
apache-2.0
Open Access
Open
Has Model Card
Yes
SOTA Tasks
Multilingual TTS; zero-shot TTS; voice cloning / voice design
Verified By
Not stated
Date Indexed
2026-05-11
Comment
Supports Algerian Saharan Arabic (aao). Treat as model support, not an aao-specific benchmark result.

Readiness (LRS) (4/7)

model id
omnivoice-tts-multi-language-high-quality-aao
Model Type
TTSderivedHugging Face card: pipeline_tag
Training Data Sources
581k-hour multilingual open-source speech dataset; includes Algerian Saharan Arabic (aao), 2.02 hours
Benchmark Used
Not stated
Benchmark Score
Not stated
Benchmark Date
Not stated
Status
Activederivedupdated within 3 years

Readiness Score Breakdown

5/5
Data Coverage59%
Model Availability100%
Benchmarks100%
Documentation92%
Recency100%

Representativeness

Gender Balance
Regional Distribution
Dialect Coverage
Inclusivity
Relations Explorer link

Related Models

model

espnet/xeus

Relevant to aao: HuggingFace language filter shows one aao model, espnet/xeus; model covers 4,024 languages and can be fine-tuned for Algerian Saharan Arabic…

1,424 languagesAlgerian Saharan Arabic(aao)XEUS self-supervised speech encoder (577M parameters)ASR / speech representation learning; E-Branchformer encoder; HuBERT-style masked prediction
HUHugging Face
Open11 May 2026
model

hubert-base-mmsulab

HubertModel · coml

1,416 languagesAlgerian Saharan Arabic(aao)HubertModel
HUHugging Face
Restricted27 Oct 2026
model

spidr-mmsulab

coml

1,416 languagesAlgerian Saharan Arabic(aao)
HUHugging Face
Restricted27 Oct 2026