Skip to main content
Audixa offers a diverse library of high-quality voices. This guide explains how to browse, select, and use voices in your API requests.

​
Voice Models

Audixa provides two model tiers:
ModelDescriptionUse Case
BaseStandard high-quality voicesGeneral TTS, high volume, cost-effective
AdvancePremium voices with cloning and emotionsCustom voices, expressive speech, dubbing

​
Listing Voices via API

Fetch available voices using the /voices endpoint: 
# Get Base model voices
curl -X GET "https://api.audixa.ai/v2/voices?model=base" \
  -H "x-api-key: YOUR_API_KEY"

# Get Advance model voices
curl -X GET "https://api.audixa.ai/v2/voices?model=advance" \
  -H "x-api-key: YOUR_API_KEY"
The model query parameter is required. Use base or advance.

​
Response Format

{
  "user_id": "user_123",
  "model": "base",
  "voices": [
    {
      "voice_id": "aura-asteria-en",
      "name": "Asteria",
      "gender": "female",
      "accent": "American English",
      "description": "Clear, professional female voice"
    },
    {
      "voice_id": "aura-orion-en",
      "name": "Orion",
      "gender": "male",
      "accent": "American English",
      "description": "Deep, authoritative male voice"
    },
    {
      "voice_id": "aura-luna-en",
      "name": "Luna",
      "gender": "female",
      "accent": "British English",
      "description": "Warm, friendly British female voice"
    }
  ]
}

​
Voice Properties

Each voice object includes:
PropertyTypeDescription
voice_idstringUnique identifier to use in /tts requests
namestringHuman-friendly voice name
genderstringmale or female
accentstringVoice accent/language (e.g., “American English”)
descriptionstringBrief description of voice characteristics

​
Using a Voice

Once you’ve selected a voice, use its voice_id in your TTS request: 
{
  "text": "Hello, this is a test.",
  "voice": "aura-asteria-en",
  "model": "base"
}
Make sure the model in your TTS request matches the model the voice belongs to.

​
Custom Voices (Advance Model)

With the Advance model, you can:

Clone Your Voice

Create a custom voice from audio samples.

Adjust Emotions

Control emotional tone: neutral, happy, sad, angry, surprised.

Fine-tune Settings

Adjust temperature and top-p for creativity control.

Branded Voices

Create unique voices for your brand.
Custom voices appear in your /voices?model=advance response with a custom: true flag.

​
Voice Selection Tips

  1. Match your audience: Choose accents that resonate with your target users
  2. Consider context: Professional content may need authoritative voices; casual content benefits from friendly tones
  3. Test before production: Generate samples with different voices before committing
  4. Check the dashboard: The Voice Library lets you preview voices interactively

​
Browse in Dashboard

For an interactive experience with audio previews:

Voice Library Dashboard

Browse, preview, and compare all available voices.