Generating Audio...
AI voice model is preparing speech. First-time synthesis may take a few moments (around 5–15 seconds), please wait...
Synthesize natural Uyghur speech using the Hugging Face QutadguBilik voice model.
Model Profile: This service integrates the piyazon/qutadgu_bilik model hosted on Hugging Face, fine-tuned on authentic Uyghur speech using the VITS/MMS-TTS neural architecture.
Number Pronunciation: The model includes automated number processing for years, ordinals, decimals, and percentages in Uyghur Arabic orthography.
Client Fallback: If the local edge proxy is unavailable, synthesis automatically uses the live Hugging Face Gradio 5 SSE pipeline.