Arabic TTS Models

SILMA Arabic TTS Models are state-of-the-art Arabic Text-to-Speech models offering natural-sounding synthesis for Modern Standard Arabic (Fus'ha) and diverse regional dialects

SILMA ABL Leaderboard
SILMA ABL Leaderboard

Try Now

Try Now

Compare to Other Models

Compare to Other Models

SILMA TTS v2.0

<300 ms TTFT

<300 ms TTFT

Low streaming latency with sub-300 ms TTFT - excluding network

Low streaming latency with sub-300 ms TTFT - excluding network

Rock-solid Performance

Rock-solid Performance

Superior stability, audio quality and naturalness

Superior stability, audio quality and naturalness

On-prem deployment

On-prem deployment

Flexible hosting options for sensitive customers

Flexible hosting options for sensitive customers

Competitive pricing

Cut your API costs by 2-6x

Tailored for Arabic

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

Control

Ability to control style variance and speed

Voices

8 brand-new voices

Voice cloning

Our models support high quality voice cloning

Dialects

We support Saudi Najdi dialect in addition to MSA/Fusha and English

Competitive pricing

Cut your API costs by 2-6x

Tailored for Arabic

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

Control

Ability to control style variance and speed

Voices

8 brand-new voices

Voice cloning

Our models support high quality voice cloning

Dialects

We support Saudi Najdi dialect in addition to MSA/Fusha and English

Open-source Models

Our Open-source TTS Models

Our Open-source TTS Models