SILMA Arabic TTS

SILMA TTS Models are state-of-the-art Arabic Text-to-Speech models and APIs offering natural-sounding synthesis for Modern Standard Arabic (Fus'ha) and Saudi Najdi dialect, purposely designed for your voice agent platform.

Create a Free Account

SILMA TTS v2.0

~170 ms TTFT

Low streaming latency with ~170ms TTFT - excluding network

Rock-solid Performance

Superior stability, audio quality and naturalness

On-prem deployment

Flexible hosting options for sensitive customers

Lower Cost

Scale your voice agent platform cost-effectively with our affordable paid plans - starting from $0.028 per minute

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

Flexible API

We provide multiple streaming options, including WebSockets, Server-Sent Events (SSE), and HTTP-based REST.