List Models

Get available audio models and their specs

GET /v1/models/list

List Models

cURL

curl --request GET \
  --url https://api.neospeech.io/v1/models/list \
  --header 'Authorization: <authorization>'

Choose the right model based on quality needs and speed requirements. Each model balances audio fidelity against processing time.

Request

curl "https://api.neospeech.io/v1/models/list" \
  -H "Authorization: Bearer sk-your-api-key"

Parameters

Authorization · string · required

Bearer token: Bearer sk-your-api-key

Response

{
  "success": true,
  "data": {
    "models": [
      {
        "id": "aurora-4",
        "name": "Aurora 4",
        "description": "Premium quality model",
        "sample_rate": "48kHz",
        "bitrate": "192kbps",
        "quality": "premium"
      }
    ],
    "total": 5
  }
}

Available models

Model	Quality	Sample Rate	Best For
aurora-4	Premium	48kHz, 192kbps	Broadcasting, professional media
aurora-3.5	High	48kHz, 96kbps	Podcasts, audiobooks, e-learning
aurora-3	Standard	24kHz, 160kbps	General content creation
turbo-3	Good	16kHz, 64kbps	Chatbots, real-time apps
mini-2	Basic	24kHz, 48kbps	IoT devices, mobile apps

When to use each

Aurora 4

Use for content where quality matters most:

• Professional video production
• Radio and TV broadcasting
• High-end marketing content
• Premium entertainment

Higher file sizes and longer processing time are worth it when audio quality is critical.

Aurora 3.5

The sweet spot for most applications:

• Podcasts and audiobooks
• Online courses and training
• Business presentations
• Professional voiceovers

Excellent quality with reasonable file sizes and processing time. Start here unless you have specific needs.

Turbo 3

When speed matters more than quality:

• Conversational AI and chatbots
• Voice assistants
• Interactive voice response (IVR)
• Real-time gaming

Lower audio quality is acceptable when users need immediate responses.

Mini 2

For resource-constrained environments:

• IoT and embedded devices
• Mobile apps with limited bandwidth
• Development and prototyping
• High-volume batch processing

Smallest files and lowest resource usage, but noticeably lower quality.

Common patterns

Get all models

const response = await fetch('https://api.neospeech.io/v1/models/list', {
  headers: { 'Authorization': `Bearer ${apiKey}` }
});

const { data } = await response.json();
console.log(`${data.total} models available`);

Choose by use case

function selectModel(useCase) {
  const modelMap = {
    'broadcasting': 'aurora-4',
    'podcast': 'aurora-3.5',
    'audiobook': 'aurora-3.5',
    'chatbot': 'turbo-3',
    'mobile': 'mini-2'
  };

  return modelMap[useCase] || 'aurora-3.5';
}

const model = selectModel('podcast');

Pick by quality priority

function selectByPriority(priority) {
  if (priority === 'quality') return 'aurora-4';
  if (priority === 'speed') return 'turbo-3';
  if (priority === 'size') return 'mini-2';
  return 'aurora-3.5'; // balanced
}

Making the choice

Start with aurora-3.5 for most projects. It offers excellent quality at reasonable speed.

Upgrade to aurora-4 only if you’re producing professional media where audio fidelity is critical. The quality difference is subtle but matters for high-end applications.

Switch to turbo-3 for conversational experiences where users expect instant responses.

Use mini-2 only when bandwidth or storage is severely limited. The quality drop is significant compared to other models.

Test your actual content with different models. What sounds good in demos might not work for your specific use case.