Habibi: Laying the Open-Source Foundation of Unified-Dialectal Arabic Speech Synthesis

Abstract  A notable gap persists in speech synthesis research and development for Arabic dialects, particularly from a unified modeling perspective. Despite its high practical value, the inherent linguistic complexity of Arabic dialects, further compounded by a lack of standardized data, benchmarks, and evaluation guidelines, steers researchers toward safer ground. To bridge this divide, we present Habibi, a suite of specialized and unified text-to-speech models that harnesses existing open-source ASR corpora to support a wide range of high- to low-resource Arabic dialects through linguistically-informed curriculum learning. Our approach outperforms the leading commercial service in generation quality, while maintaining extensibility through effective in-context learning, without requiring text diacritization. We are committed to open-sourcing the model, along with creating the first systematic benchmark for multi-dialect Arabic speech synthesis. Furthermore, by identifying the key challenges in and establishing evaluation standards for the process, we aim to provide a solid groundwork for subsequent research.

Figure 1  Our open-source unified-dialectal model (Habibi) outperforms ElevenLabs' commercial TTS service: the latest Eleven v3 (alpha) (11Labs-3a).
WER-O and WER-S are the word error rates evaluated using Meta Omnilingual-ASR-LLM-7B and dialect-specific ASR models, respectively.

This page is for research demonstration purposes only.

Zero-Shot Speech Synthesis Performance

This page is for research demonstration purposes only.