Get Started
Speech
Overview
Gan.AI provides a powerful text-to-speech API platform that supports 22 Indic languages and English, offering developers the ability to integrate natural and expressive speech synthesis into their applications.
Key Features
Multilingual Support
- Comprehensive coverage of 22 official Indic languages plus English.
- Code-mixed language support allowing mixing of different languages in the same API call.
- First model in the world to support all official Indic languages.
Voice Options
- 5 free voices available for basic usage.
- Enterprise-level voice cloning capabilities.
- Cross-lingual voice cloning (under restricted beta).
Getting Started:
1. API Key Generation
- Visit playground.gan.ai and select Create API Key to generate your API key.!
- With just one click, copy your key and you’re ready to go!
- Use this key to authenticate all API requests. For detailed setup and usage instructions, refer to our developer documentation.
2. Language Support
Experience Text-to-Speech Like Never Before!
Discover our groundbreaking text-to-speech capabilities that support all 22 official Indic languages, making us the first in the world to offer such comprehensive coverage. Our diverse language offerings include:
- Assamese
- Bengali
- Bodo
- Dogri
- Gujarati
- Hindi
- Kannada
- Kashmiri
- Konkani
- Maithili
- Malayalam
- Manipuri
- Marathi
- Nepali
- Odia
- Punjabi
- Sanskrit
- Santali
- Sindhi
- Tamil
- Telugu
- Urdu
With our extensive selection, you can effortlessly create engaging audio content in your preferred language, bridging communication and fostering connection across cultures. Experience the power of our text-to-speech technology today!
3. Technical Specifications
Model Details
- Myna-mini TTS model for basic usage
- Medium and large models in development
- Ultra-low latency streaming mode (coming soon)
4. Enterprise Features
Advanced Capabilities
- Custom voice cloning
- High-volume processing
- Dedicated account management
- Custom integration support