๐ŸŽ™๏ธ Arabic Text-to-Speech | Spark Model

High-quality Arabic TTS with voice cloning. Diacritized text (ุชุดูƒูŠู„) required.

Model: IbrahimSalah/Arabic-TTS-Spark

๐ŸŽต Reference Audio
0.1 1.5
0.1 1
100 500
0.01 0.2

โ„น๏ธ Requirements

  • Diacritized text is required (ุชุดูƒูŠู„/ุชุดูƒูŠู„)
  • Reference audio: 5-30 seconds, clear speech
  • Use AI (ChatGPT/Claude) or online tools to add diacritics

๐Ÿ”— Resources
Examples
๐Ÿ“ Text to Synthesize (Arabic with Tashkeel) ๐Ÿ“„ Reference Transcript (with Tashkeel)