API Documentation
Build powerful text-to-speech applications with our simple REST API. Generate audio asynchronously, stream it in real time, or integrate via MCP.
One unified API and TTS aggregation platform instead of stitching together provider-specific integrations. Access voices from Google Cloud/Gemini TTS, Amazon Polly, Kokoro, and more — with harmonized voice IDs, standard output formats, async jobs, safe retries, enterprise webhooks, and storage that scales with your plan. Also advanced features accessible including creating voice playlist sharing, bookmarks, library management with tags/collections and more.
{
"text": "Hi there! Its a pleasure to have you here...",
"voice_id": "google:en-US-Chirp3HD-Charon"
}This docs playground is an anonymous demo, so it returns a temporary audio_url for direct playback. Real API v1 integrations should use the authenticated audio_endpoint from /api/v1/tts/{job_id} instead of depending on signed storage URLs.
Demo endpoint. Sign up for your API key.
Quickstart
Get started in 2 minutes
API Reference
Full endpoint documentation (46 endpoints)
Provider Capabilities
Feature support by provider and tier
Webhooks
Real-time job notifications
Examples
Code samples in multiple languages
MCP
Connect AI assistants via Model Context Protocol
Base URL
https://aitts.theproductivepixel.com/api/v1Authentication
All requests require an API key in the Authorization header:
Authorization: Bearer tts_your_api_keyResponse Format
All responses are JSON with success boolean and data or error object.
Authentication Models
The API supports two authentication schemes depending on the context:
- API Key — used for all REST API calls (generation, polling, audio retrieval, voice listing, usage). Create keys from your Dashboard under the API tab. Keys start with
tts_and are passed via theAuthorization: Bearerheader. - Firebase ID Token — used for webhook configuration and account-level settings. Obtain a token by signing in with Firebase Auth, then pass it as a
Bearertoken in the Authorization header. This is only required for webhook management endpoints, not for TTS generation.
Frequently Asked Questions
Need help? Contact support
© 2026 AI TTS Microservice. All rights reserved.