Arabic Dialects · Text to Speech

Tunisian · تونسي

Tunisian Arabic
Text to Speech

Hamsa TTS speaks Tunisian the way people actually speak it, with all its speed, rhythm, and distinctive vowel deletion. Authentic Tunisian voices, mixed-text support, and under 300ms streaming.

dialect: "tunisian"4 voices · streaming · SSML

4.1 / 5

MOS naturalness on Tunisian speech

4

Native Tunisian Arabic voices

<300ms

First audio chunk latency

12M+

Native Tunisian Arabic speakers

Coming Soon

Demo launching soon

The interactive demo for this dialect is coming soon. Sign up to be notified when it launches.

Join the waitlist →

Dialect overview

Synthesizing Tunisian Arabic

Tunisian Arabic is one of the fastest and most phonologically dense Arabic dialects, spoken by more than 12 million people. Layered on top is a multilingual heritage of French, Italian, Amazigh, and Turkish. For TTS serving Tunisian users, in tourism, telecom, or digital services, the voice has to sound like Tunisia, not a slowed-down newsroom reading.

Key phonological features Hamsa TTS reproduces natively:

  • Fast speech rate with systematic short-vowel deletion and syllable compression.
  • Tunisian stress and intonation patterns, not MSA broadcast cadence.
  • French and Italian words pronounced naturally inside Tunisian sentences.
  • Colloquial expressions: "برشا" (a lot), "توا" (now), "باهي" (OK) spoken naturally.

Native speakers

12M+

Tunisia

Hamsa MOS score

4.1/5

naturalness on Tunisian speech

Streaming latency

<300ms

first audio chunk

Available Tunisian voices

4

female & male · multiple styles

The problem

Why generic Arabic TTS sounds
unnatural to Tunisian users

Tunisian listeners notice a slow, formal MSA voice immediately, and trust it less.

MSA pronunciation applied to Tunisian text

Generic Arabic TTS engines are usually trained on Modern Standard Arabic, so they apply MSA pronunciation when reading Tunisian text. The result sounds formal and unnatural to Tunisian listeners, missing the speed and the vowel-deletion rhythm that define Tunisian.

Tunisian intonation and rhythm mismatch

Tunisian has a fast rhythm with systematic short-vowel deletion. MSA-trained models produce a slow, formal delivery that is intelligible but sounds synthetic, nothing like how Tunisians actually speak.

Hybrid vocabulary and French terms

Tunisian TTS input is often written as a blend of Arabic, French, and Italian. Engines trained on MSA struggle to pronounce this mix naturally, producing uneven, inconsistent speech.

No authentic Tunisian voices

Most Arabic TTS providers offer Gulf or Egyptian voices labelled "Arabic", while Tunisian options are rare or missing. When they do exist, they are usually MSA voices with a Tunisian accent layered on.

The solution

How Hamsa synthesizes
authentic Tunisian speech

✓

Native Tunisian speaker data

Trained on thousands of hours of native Tunisian speech covering fast everyday conversation, professional delivery, and expressive Tunisian, at its natural speed and with its vowel deletion intact.

✓

Tunisian phonology engine

A voice model designed for Tunisian that understands its natural pronunciation, from high speech rate and vowel deletion to Tunisian stress patterns and hybrid vocabulary. Built on Tunisian speech from the start.

✓

Hybrid Tunisian text normalization

A dedicated layer for multilingual Tunisian text recognizes French and Italian words written in Arabic script and informal spellings, and prepares the text before synthesis.

✓

Style and emotion control

Each voice supports multiple speaking styles via the `style` API parameter or SSML tags. Use `style: "professional"` for IVR, `style: "warm"` for customer service, or `style: "expressive"` for tourism apps.

Tunisian Arabic voices

Four native Tunisian voices

All trained on native Tunisian speakers. All supporting streaming, SSML, and style control.

M
Male

mounir

Professional

Warm, professional Tunisian voice suited for IVR, customer service, and digital services.

voice: "mounir-tn"
F
Female

farah

Warm

Natural Tunisian cadence for chatbots, tourism apps, and notifications.

voice: "farah-tn"
A
Male

ali

Authoritative

Clear, measured Tunisian delivery for media, announcements, and e-learning.

voice: "ali-tn"
N
Female

nesrine

Dynamic

Wide expressive range, from excitement and empathy to calm, for consumer-facing apps.

voice: "nesrine-tn"

Capabilities

Everything you need for
Tunisian Arabic TTS

✓

Native Tunisian Pronunciation

Synthesized speech follows natural Tunisian pronunciation, including its distinctive speed, vowel deletion, and Tunisian stress patterns, instead of applying MSA rules.

✓

Multiple Tunisian Voices

Four production voices across gender and speaking style. All trained on native Tunisian speakers.

✓

Emotional Range

Adjust tone from calm and professional to warm and expressive, via SSML tags or the `style` API parameter.

✓

Streaming Synthesis

First audio chunk arrives in under 300ms. Stream to browser, phone, or contact center systems without waiting for the full utterance to render.

✓

SSML Support

Fine-grained control over pauses, pronunciation, speaking rate, and pitch, plus say-as dates and numbers read the way Tunisians say them.

✓

Custom Lexicon

Override pronunciation for brand names, technical terms, and French-Tunisian words. Tunisian-specific phonetic notation supported.

Voice examples

Real Tunisian Arabic.
Synthesized naturally.

IVR · Mounir (Male)

مرحبا بيك في خدمة الحرفاء، تحب تحكي مع مستشار توا ولا تخلّي رسالة؟

"Welcome to customer service. Would you like to speak with an advisor now or leave a message?"

mounir-tn · professional

Notification · Farah (Female)

الكوموند متاعك خرجت، وباش توصلك في ظرف ساعتين. تنجم تتبّعها من الأبليكاسيون.

"Your order is on its way and will reach you within two hours. You can track it from the app."

farah-tn · warm

Tourism · Ali (Male)

اليوم باش نحكيو على تاريخ قرطاج، وعلاش تعتبر من أهم المواقع في تونس.

"Today we'll talk about the history of Carthage, and why it's considered one of the most important sites in Tunisia."

ali-tn · authoritative

Use cases

Where Tunisian Arabic TTS
delivers results

Tourism & Hospitality

Voice Apps for Tourism

Tunisia is a major tourist destination. Voice reception systems and digital assistants in hotels and tourist sites that speak authentic Tunisian improve the experience for local visitors and let them be served in their own dialect.

IVR & Contact Centers

IVR for Tunisian Digital Services

Replace formal MSA IVR prompts with natural Tunisian voices. Callers recognize the dialect immediately, which makes every interaction clearer and smoother.

Media & Publishing

Tunisian Audio Content

Turn articles, newsletters, and written Tunisian content into natural audio for users who prefer to listen.

E-learning & EdTech

Tunisian Educational Audio

Generate natural Tunisian narration for e-learning content, explainer videos, and interactive learning apps.

Naturalness benchmark

Natural Tunisian Arabic speech at the highest quality

Evaluated by native Tunisian listeners on a 5-point Mean Opinion Score (MOS) scale. Higher score means more natural-sounding speech.

MOS Naturalness Score · higher is better (max 5.0)

Hamsa TTS (Tunisian)us4.1
Generic Arabic TTS2.9
MSA-based synthesis2.4
Cloud TTS (Arabic)3.1

Mean Opinion Score rated by native Tunisian listeners · 2024 · Higher is better

Architecture

How it works

01

Text in

Send Tunisian Arabic text via REST or WebSocket. Colloquial Tunisian, mixed Arabic and French, SSML markup: all accepted. A Tunisian-specific normalization layer handles informal spelling and French or Italian words in Arabic script before synthesis.

02

Tunisian synthesis

The selected Tunisian voice converts normalized text to audio using Hamsa's Tunisian phonology engine. Style, speaking rate, and pitch adjust according to the `style` parameter or inline SSML tags.

03

Audio out

MP3, WAV, or Opus audio streams back in real time. First chunk in under 300ms. Pipe directly to WebRTC, telephony, browser audio, or a media player, with no buffering required.

Developer API

Three lines to Tunisian Arabic speech synthesis

Pass your Tunisian Arabic text, pick a Tunisian voice, and stream audio. No phonetic transcription, no MSA normalization step, no dialect adapter config.

Read the API docs →
tunisian-tts.tsstreaming
import { Hamsa } from '@hamsa-ai/sdk';

const audio = await hamsa.tts.synthesize({
  text:    'أهلاً بيك، شنية الأخبار؟',
  voice:   'mounir-tn',
  dialect: 'tunisian',
  style:   'warm',
});

// → streams PCM audio · first chunk <300ms

Related services

More Hamsa for Tunisian Arabic

Why Hamsa

Built for Arabic from the ground up

✓

Native, not adapted

Hamsa trains on real Tunisian speaker data, not an English or MSA TTS model fine-tuned for Arabic. The phonology, prosody, and rhythm are all Tunisian from the start.

✓

Enterprise-grade SLA

99.9% uptime, SOC 2 Type II compliance, and MENA data residency. Your text and audio stay in-region.

✓

Fastest Arabic streaming

Under 300ms first-chunk latency in production. Real-time synthesis that keeps pace with conversational turn-taking.

✓

13+ dialects, one API

Switch from Tunisian to Moroccan, Algerian, or any other dialect with a single parameter change. No separate integrations, no per-dialect contracts.

FAQ

Tunisian Arabic TTS:
frequently asked

Does Hamsa TTS sound like a real Tunisian speaker?

Yes. Hamsa's Tunisian Arabic voices are trained on native Tunisian speakers and use a voice model designed specifically for Tunisian. The output has authentic Tunisian speed and rhythm and natural colloquial pronunciation, including the vowel deletion and distinctive stress that define how Tunisians actually speak.

What is the difference between Tunisian TTS and generic Arabic TTS?

Generic Arabic TTS engines are trained on Modern Standard Arabic, so when they process Tunisian text they may apply MSA pronunciation, and the voice sounds slow, formal, and unnatural. Hamsa trains on authentic Tunisian speech data with a dedicated voice model, producing speech that reflects real Tunisian delivery at its full speed and rhythm.

How fast is Hamsa's Tunisian Arabic TTS?

Hamsa streams audio in real time. The first audio chunk arrives in under 200ms from the API call, so IVR systems, voice assistants, and tourism apps can start speaking almost instantly with no noticeable delay.

Can I control the speaking style or emotion?

Yes. Each voice supports multiple speaking styles via the `style` API parameter or SSML tags. Use `style: "professional"` for IVR, `style: "warm"` for customer service, or `style: "expressive"` for consumer and tourism apps.

Does Hamsa TTS handle mixed Tunisian and French text?

Yes. A dedicated layer processes Tunisian text before synthesis, including French and Italian words written in Arabic script, numbers, dates, and informal spellings. You can pass Tunisian text as it is, directly.

Explore more

13+ Arabic dialects, supported

Partner ecosystem

Trusted Across the
Technology Ecosystem

Hamsa works with leading technology companies, integrators, and solution providers to bring enterprise Voice AI to organizations across the region.