Overview
Capability Overview
Learn about TTS capabilities, models, and use cases
Models
Explore TTS models and their specifications
API Reference
Technical API documentation for developers
Quickstart
Get started with TTS in minutes
Key features
Arabic dialect support
Our TTS models are specifically optimized for Arabic speech:- Multiple dialects: Egyptian, Gulf, Levantine, North African, and Modern Standard Arabic
- Natural pronunciation: Proper handling of Arabic phonetics and pronunciation rules
- Code-switching: Seamless handling of mixed Arabic-English text
- Diacritical marks: Support for tashkeel and proper pronunciation
High-quality voices
- Pre-built Arabic voices optimized for different dialects
- Custom voice cloning for brand consistency
- Voice customization options
- Gender and age variety
Flexible integration
- REST API for programmatic access
- Web interface via Media Platform
- Real-time streaming support
- Multiple audio format options (MP3, WAV, PCM)
Use cases
Media & content creation
Generate high-quality Arabic voiceovers for:- Video content and advertisements
- Podcasts and audio content
- Social media content
- Marketing materials
Accessibility
Make Arabic content accessible:- Audio versions of written content
- Screen readers for Arabic websites
- Educational materials
- Documentation narration
Voice agents & IVR
Power conversational applications:- AI voice agents for customer service
- IVR systems with natural Arabic speech
- Automated phone systems
- Voice assistants
E-learning
Create engaging educational content:- Course narration in Arabic
- Language learning applications
- Training materials
- Interactive lessons
Models
Hamsa offers two TTS models optimized for different use cases:TTS Standard
Best for qualityHigh-quality Arabic speech synthesis with natural pronunciation and intonation.
- 10,000 character limit
- ~300-500ms latency
- Multiple Arabic dialects
- Highest quality output
TTS Realtime
Best for speedUltra-fast model optimized for real-time voice agents and interactive applications.
- 5,000 character limit
- ~150-200ms latency
- Arabic dialects + English
- Conversational AI optimized
Supported languages
Arabic Dialects:- Egyptian Arabic (arz)
- Gulf Arabic (afb) - Saudi, UAE, Kuwait, Bahrain, Qatar, Oman
- Levantine Arabic (apc) - Syrian, Lebanese, Jordanian, Palestinian
- North African Arabic (arq/ary) - Moroccan, Algerian, Tunisian, Libyan
- Modern Standard Arabic (arb)
- English (US) (eng)
Audio formats
Hamsa TTS supports multiple output formats:- MP3: Standard compressed audio (22.05kHz - 44.1kHz)
- WAV: Uncompressed audio (16kHz - 48kHz)
- PCM: Raw audio data (16-bit, 16kHz - 48kHz)
- μ-law: Telephony optimized (8kHz)
Getting started
Next steps
Quickstart Guide
Build your first TTS integration
Voice Options
Explore available voices
Voice Cloning
Learn about custom voice cloning
SSML Guide
Advanced text formatting with SSML
FAQ
Which model should I use?
Which model should I use?
Use TTS Standard for high-quality media content, voiceovers, and when audio quality is paramount. Use TTS Realtime for voice agents, interactive applications, and when low latency is critical.
Can I mix Arabic and English in the same text?
Can I mix Arabic and English in the same text?
Yes, our models naturally handle code-switching between Arabic and English. The model automatically detects and pronounces each language correctly.
How do I choose the right dialect?
How do I choose the right dialect?
Choose the dialect that matches your target audience. Egyptian Arabic has wide recognition across the Arab world. Gulf Arabic is preferred in GCC countries. Levantine is common in the Levant region. For formal content, use Modern Standard Arabic (MSA).
Can I clone my own voice?
Can I clone my own voice?
Yes, Hamsa supports custom voice cloning. See our voice cloning guide for more information.
What's the character limit?
What's the character limit?
TTS Standard supports up to 10,000 characters per request. TTS Realtime supports up to 5,000 characters. For longer content, split into multiple requests.