Introduction
Welcome to Gan.AI API Platform, the ultimate tool for developers looking to integrate advanced text-to-speech and voice cloning capabilities into their applications. Our platform makes it simple to transform written text into natural, expressive speech, enhancing user experiences across a range of platforms.
With Gan.AI API, you can effortlessly incorporate high-quality, realistic voice synthesis into your projects. Our service offers a diverse selection of voices, languages, and customization options, allowing you to tailor the audio output to fit your specific needs. From lifelike human voices to various accents and tones, our API provides the flexibility to bring your ideas to life.
Dive into the future of voice technology with Gan.AI API and let your text speak for itself.
Supported languages
Experience text-to-speech like never before with our diverse language offerings! We cover a rich selection of languages, from Assamese to English, including Bengali, Bodo, Dogri, Gujarati, Hindi, Kannada, Kashmiri, Konkani, Maithili, Malayalam, Manipuri, Marathi, Nepali, Odia, Punjabi, Sanskrit, Santali, Sindhi, Tamil, Telugu, and Urdu
.
Dive into a world of multilingual possibilities!
Generating Api Keys
Visit our website to generate the API key for interacting with our API endpoints.
Text-to-Speech
This documentation provides detailed instructions on how to interact with Gan.AI API using the generated API key. First, use the GET /v1/voices
endpoint to retrieve a list of available voices and their unique identifier i.e. voice_id
. Choose the appropriate voice for your needs and note its voice_id.
Next, use the POST /v1/tts
endpoint to send a request that includes your chosen voice_id and the text you want to convert into speech. The API will process your request and return an audio wav file
with the generated speech.
To review the history of generated text-to-speech requests, use the GET /v1/tts/history
API endpoint.