KasbahTTS V0

--- language: - ar tags: - tts - text-to-speech - arabic - algerian-arabic - dardja - f5-tts - habibi-tts - speech-synthesis - zero-shot - voice-cloning license: mit pipeline_tag: text-to-speech --- <div align="center"> <img src="media/background.jpg" alt="KasbahTTS — صوت القصبة" width="100%"> <br><br> [](https://github.com/SWivid/F5-TTS) [](https://huggingface.co/SWivid/Habibi-TTS) [](LICENSE) []() </div> --- ## Overview **KasbahTTS** is the first open-source Text-to-Speech model purpose-built for **Algerian Dardja** (الدارجة الجزائرية). Most Arabic TTS systems only speak Modern Standard Arabic — a language nobody uses on the street. KasbahTTS speaks like real Algerians do: the Dardja of Algiers' alleyways, the warmth of Oran's markets, the rhythm of Constantine's conversations. Built on the **F5-TTS architecture** (DiT-based flow matching) and fine-tuned from **Habibi-TTS**, KasbahTTS brings Algerian speech synthesis into the open-source world. > **أول موديل TTS مفتوح المصدر يهدر بالدارجة الجزائرية.** --- ## Audio Samples Listen to KasbahTTS in action — each sample shows the **reference voice** the model clones from, followed by the **generated speech**: ### Sample 1 | | Audio | |---|---| | **Reference** | <audio controls src="media/1r.wav">Your browser does not support audio.</audio> | | **Generated** | <audio controls src="media/1.wav">Your browser does not support audio.</audio> | ### Sample 2 | | Audio | |---|---| | **Reference** | <audio controls src="media/2r.mp3">Your browser does not support audio.</audio> | | **Generated** | <audio controls src="media/2.wav">Your browser does not support audio.</audio> | ### Sample 3 | | Audio | |---|---| | **Reference** | <audio controls src="media/3r.mp3">Your browser does not support audio.</audio> | | **Generated** | <audio controls src="media/3.wav">Your browser does not support audio.</audio> | --- ## Model Details | | | |---|---| | **Model** | KasbahTTS V0 | | **Task** | Text-to-S...