The Foundational Saudi Voice Engine for Voice Agent Platforms

Bring hyper-realistic Saudi Najdi & Bilingual speech to your voice orchestration pipeline. SILMA Saudi TTS v2.0 delivers sub-300 ms TTFT streaming infrastructure built explicitly for voice agent providers, telephony platforms, and conversational AI developers targeting the MENA market

Try Now

Compare to Other Models

Saudi TTS v2.0 (Najdi Dialect)

Sub-300ms Native Streaming

Eliminate conversational lag. Engineered for seamless real-time integration with industry-leading Time-to-First-Token

Rock-solid Performance

Superior stability, audio quality and naturalness

On-Prem & VPC Deployments

Deploy on-premise or within your own cloud infrastructure. Fulfill strict GCC data residency and compliance laws for your enterprise and government clients

2-6x Lower Cost

Scale your voice agent platform cost-effectively. Cut yourAPI costs by 2-6x

Bilingual Fluidity

Native, code-switching support for Saudi Najdi, Modern Standard Arabic (Fusha), and English within a single, unified pipeline

Tailored for Arabic

Where others generalize, our models specialize, offering unmatched depth in dialectal pronunciation

Control

Ability to control style variance and speed

Voice cloning

Our models support high quality voice cloning

Voices

8 brand-new voices