Skip to main content
Welcome to the Audixa API Reference. This section provides detailed documentation for all API endpoints.

​
Base URL

All API requests are made to:

​
Authentication

Authenticated endpoints accept an API key in the X-API-Key header:

Learn More

See the Authentication guide for details on obtaining and using API keys.
Authorization: Bearer YOUR_API_KEY is also accepted. Keep API keys in server-side secrets and never ship them in public browser code.

​
Language Examples

No Audixa SDK package is required. The language guides use the REST API directly:

Python requests

Create and poll generations with requests.

JavaScript fetch

Use the native fetch API in a server runtime.
Fixed voice previews are available at audixa.ai/voices. Creating a dashboard or API generation requires a minimum $10 top-up or an active subscription.

​
Async Workflow

Audixa uses an asynchronous workflow for audio generation:
1

Submit TTS Request

POST to /v3/tts with non-empty text, a compatible voice_id, model, and audio_format. Receive a generation_id and initial status IN_QUEUE. Each generation is billed for at least 30 characters (8 tokens).
2

Poll Status

GET /v3/tts with your generation_id until status is COMPLETED.
3

Download Audio

Fetch the audio file from the returned audio_url.

​
Available Endpoints

POST /tts

Start a text-to-speech generation job.

GET /tts (Status)

Check the status of a generation job.

GET /voices

List available voices for a model.

GET /history

Retrieve generation history.

WS /stream

Real-time audio streaming.

​
Response Format

All responses are JSON. Successful responses return status 2xx with the requested data. Success example:
Error example:

Quickstart

Create and poll an authenticated generation.

Error Codes

Understand and handle API errors.

Rate Limits

Learn about request limits and best practices.

Pricing

Understand paid generation and wallet expiry.