API for generating audio from text using a specific voice style and model.
An API key is a token that you provide when making API calls. Include the token in a header parameter called apiKey.
Example: apiKey: 123
Generates audio from text based on a specific model, voice style, and configuration parameters.
The ID of the model to use for generation. Available options:
Example:silma-tts-pro-ksa-large
The text content to be generated into audio (with or without tashkeel).
Example:بِسْمِ اللَّهِ الرَّحْمَـٰنِ الرَّحِيمِ
Example:Sulaiman
Number of function evaluation steps (speed/quality trade-off). Recommended to be fixed at 16.
Default:16
Random seed for reproducibility. Changing the seed slightly changes the style of the generated audio.
Default:42
Whether to strip silence from the output.
Default:false
The speed of the speech, add or subtract increments of 0.1 - if needed.
Default:1.1
Whether to use Exponential Moving Average weights [false for KSA models. true for MSA models].
Default:false
Whether to convert numbers in text to words.
Default:true
A dictionary of words and their custom phonetic pronunciations (using tashkeel).
Example:{"اكل":"اُكِل"}
Base64 encoded string of a custom reference audio file (optional).
This indicates that you have added custom pronunciation overrides to your account via the app. Enabling this feature will automatically customize the model based on your overrides without sending the overrides word mapping in each API call
Default:false
Optional user identifier, needed only for pronunciation overrides and loading custom voices. Find it here https://app.silma.ai/api-keys
Default:true
Successful generation
The generated audio file encoded in Base64.
The processed text included in the response.
The time taken by the server to process the inference.