๐Ÿ‡ธ๐Ÿ‡ฆ NAMAA-Saudi-TTS

NAMAA-Saudi-TTS is a Saudi Arabic Text-to-Speech (TTS) model built on top of the Chatterbox Multilingual TTS architecture.

It is optimized for natural Saudi dialect speech, focusing on conversational Arabic rather than Modern Standard Arabic (MSA).


๐Ÿ”Š Live Demo

๐Ÿ‘‰ https://huggingface.co/spaces/omarelshehy/NAMAA-Saudi-Voice


โœจ Key Features

  • Saudi Arabic speech synthesis (language_id = "ar")
  • Natural conversational prosody
  • Dialect-aware pronunciation (Saudi style)
  • Optional reference audio for:
    • Voice cloning
    • Style / tone transfer
  • GPU accelerated inference

๐Ÿ—ฃ๏ธ Example Text

ุขุจูŠ ุฃุฑูˆุญ ุงู„ุจู‚ุงู„ุฉ ุฃุดุชุฑูŠ ูƒู… ุบุฑุถ ูˆุฃุฑุฌุน ุจุณุฑุนุฉ.
Downloads last month
14
Safetensors
Model size
0.5B params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for muaadh019/voice-arabic-tts

Finetuned
(47)
this model

Space using muaadh019/voice-arabic-tts 1