Skip to main content
Get started with Faseeh’s Text-to-Speech API in three simple steps.

​
Prerequisites

  • An API key from the Faseeh dashboard
  • A model ID (retrieved from /models endpoint)
  • A voice ID for text-to-speech generation

​
Step 1: Get Your API Key

Create an API key in the Faseeh dashboard. You’ll use this key to authenticate all API requests.
Keep your API key secure and never expose it in client-side code or public repositories.

​
Step 2: Retrieve Available Models

First, get a list of available models: 
curl -X GET "https://api.faseeh.ai/api/v1/models" \
  -H "x-api-key: YOUR_API_KEY"
Response: 
[
  {
    "id": "uuid",
    "model_id": "model_123",
    "model_name": "Faseeh Arabic v1",
    "cost": 0.0001,
    "description": "High-quality Arabic voice synthesis"
  }
]

​
Step 3: Generate Speech

​
Option A: Streaming Audio Output

Generate speech with streaming PCM16 audio: 
curl -X POST "https://api.faseeh.ai/api/v1/text-to-speech/MODEL_ID" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice_id": "VOICE_ID",
    "text": "مرحبا بك في فصيح كيف يمكنني مساعدتك اليوم",
    "stability": 0.5,
    "streaming": true
  }' \
  --output audio.pcm

​
Option B: Complete Audio File (WAV)

Generate speech and receive a complete WAV file: 
curl -X POST "https://api.faseeh.ai/api/v1/text-to-speech/MODEL_ID" \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "voice_id": "VOICE_ID",
    "text": "مرحبا بك في فصيح كيف يمكنني مساعدتك اليوم",
    "stability": 0.5,
    "streaming": false
  }' \
  --output audio.wav

​
Option C: WebSocket Streaming

For real-time streaming, use WebSocket: 
const ws = new WebSocket('wss://api.faseeh.com/api/v1/text-to-speech?x-api-key=YOUR_API_KEY');

ws.onopen = () => {
  // Initialize connection
  ws.send(JSON.stringify({
    type: 'initConnection',
    model_id: 'MODEL_ID',
    voice_id: 'VOICE_ID',
    voice_settings: {
      stability: 0.5
    }
  }));
};

ws.onmessage = (event) => {
  const data = JSON.parse(event.data);
  
  if (data.type === 'connectionInitialized') {
    // Send text for generation
    ws.send(JSON.stringify({
      type: 'text',
      text: 'مرحبا بك في فصيح كيف يمكنني مساعدتك اليوم',
      try_trigger_generation: true
    }));
  } else if (data.audio) {
    // Handle audio chunks (base64 encoded)
    const audioData = atob(data.audio);
    // Process audio chunk
  }
};

​
Next Steps

Explore Models

Learn about available models

Text-to-Speech Guide

Deep dive into text-to-speech

API Reference

Complete API documentation

Voice Cloning

Create custom voices