Version: 1.0.0

• OpenAPI Spec

Aakash AI - TTS API Documentation

Text-to-Speech (TTS) API

This API provides text-to-speech conversion capabilities using Google Gemini TTS. Generated audio files are automatically uploaded to Google Cloud Storage and a publicly accessible URL is returned.

Quick Start

1. Get your API key (user UUID) from the admin panel
2. Make a POST request to /tts with your text
3. Receive a Google Cloud Storage URL to your audio file

Authentication

All API endpoints require authentication via the Authorization header.

curl -X POST "https://api.example.com/ai/api/v2/tts" \
  -H "Authorization: your-user-uuid" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hello, world!"}'

Features

• 29 prebuilt voices - Male and female options
• Multi-language support - English, Hindi, Nepali
• High-quality audio - WAV format, 24kHz sample rate
• Cloud storage - Automatic Google Cloud Storage upload with public URLs
• Fast processing - Typically under 2 seconds

Rate Limits

Limit Type	Value
Max text length	5000 characters
Audio format	WAV (PCM 16-bit, mono)
Sample rate	24000 Hz

Authentication

API Key: ApiKeyAuth

Your user UUID serves as the API key.

Can be provided with or without 'Bearer ' prefix:

• Authorization: your-user-uuid
• Authorization: Bearer your-user-uuid

Security Scheme Type:	apiKey
Header parameter name:	Authorization

Contact

API Support: support@example.com

License

MIT