Model APIs Overview

slng.ai provides a simple, unified API for accessing state-of-the-art voice models. Our APIs allow you to transcribe audio, generate speech, and identify speakers in your applications.

Making API Requests

All slng.ai model APIs follow a consistent pattern. You can make requests to our models using standard REST API calls with JSON payloads. Each model has its own endpoint and accepts specific parameters.

Available Models

Example: Transcribing Audio

curl -X POST https://api.slng.ai/v1/us/whisper \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: multipart/form-data" \
  -F "audio=@recording.mp3" \
  -F "language=en" \
  -F "task=transcribe"

Example: Generating Speech

curl -X POST https://api.slng.ai/v1/us/koroko \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Welcome to slng.ai, where voice models run where you need them.",
    "voice": "emma",
    "output_format": "mp3"
  }' \
  --output speech.mp3

Authentication

All API requests require authentication using an API key. You can obtain your API key from the slng.ai dashboard after signing up.

Regional Deployment

slng.ai allows you to choose where your models run. This helps with data residency requirements, compliance with local regulations, and reducing latency.