Models
Munsit offers state-of-the-art Arabic voice synthesis models designed to handle various dialects and use cases. List them with one call, then pass the model_id to any text-to-speech endpoint.
Meet the model
Faseeh is Munsit's Arabic voice synthesis model — natural, high-quality speech across multiple Arabic dialects. Pass its model_id to any text-to-speech endpoint.
| Model | model_id | Highlights |
|---|---|---|
| Faseeh High-quality Arabic voice synthesis model |
faseeh-v1-preview |
Natural-sounding Arabic speech · Multiple Arabic dialects supported · High-quality voice generation · Optimized for clarity and naturalness |
List models
Retrieve a list of all available text-to-speech models. This endpoint does not return speech-to-text models — there is no discovery endpoint for those. The ASR models are munsit (default) and munsit-en-ar, passed as the model field on transcription requests.
Retrieve a list of all available voice synthesis models. Requires API key authentication via the x-api-key header. Returns an array of model objects.
Response fields
Each model object contains:
| Field | Type | Description |
|---|---|---|
model_id | string | Model identifier used in API calls |
model_name | string | Human-readable model name |
description | string | null | Detailed description of the model |
Usage
Use the model_id from the response in text-to-speech generation endpoints: POST /text-to-speech/:model_id (HTTP endpoint) or WS /text-to-speech (WebSocket endpoint — include model_id in the initConnection message).
Go further
Working with an AI assistant? Every page is available as Markdown: add .md to the URL, or send an Accept: text/markdown header. For the whole documentation in one request, point it at llms-full.txt; the page index is llms.txt. Or use Copy Page, top right.