README.md

metadata

title: KasbahTTS V0 — Algerian Dardja TTS
emoji: 🎙️
colorFrom: red
colorTo: green
sdk: gradio
sdk_version: 6.20.0
app_file: app.py
pinned: false
license: mit
short_description: Zero-shot Algerian Dardja (الدارجة) text-to-speech
models:
  - MenaVoice/KasbahTTS-V0
tags:
  - text-to-speech
  - arabic
  - algerian-arabic
  - dardja
  - f5-tts
  - voice-cloning

KasbahTTS V0 — Algerian Dardja TTS

Interactive demo for MenaVoice/KasbahTTS-V0, the first open-source text-to-speech model built for Algerian Dardja (الدارجة الجزائرية).

Give it a few seconds of any voice and some Dardja text, and it speaks that text in that voice.

How it works

Built on F5-TTS (DiT-based flow matching), fine-tuned from Habibi-TTS on real Algerian conversational speech. Weights are pulled at runtime from the model repo, so this Space does not carry its own copy.

Limitations

• Arabic script only — no French code-switching
• No digits — spell numbers out (ثلاثة, not 3)
• No diacritics (تشكيل)
• May occasionally repeat words; try nfe_step=64 or shorter segments

---

من القصبة للعالم — From the Kasbah to the world