# Inworld TTS 1.5 Max - Core.Today AI API

> Inworld's highest-quality realtime TTS with under 200ms latency. Supports SSML break tags for pauses, emotion markups like [happy], and 15 languages.

- **Provider**: Inworld
- **Model ID**: inworld/tts-1.5-max
- **Category**: Audio & TTS
- **Credits**: 24 per 1000 characters (0.023 credits/char, billed per character)
- **Speed**: Fast
- **Quality**: High

## Features
- Under 200ms median latency
- Emotion markups: [happy], [sad], [angry]
- SSML break tags for precise pauses
- 15 language support
- Very low per-character price

## Use Cases
- Production voice agents at scale
- Real-time conversational AI
- Emotion-aware assistant voices
- Low-cost bulk narration
- Streaming content voiceovers

## API Endpoint

Base URL: https://api.core.today/v1
Create Prediction: POST /predictions
Get Status: GET /predictions/{job_id}

## Authentication
Header: X-API-Key: YOUR_API_KEY

## Input Parameters

### Required
- **text**: string - Text to convert (max 2,000 chars). Supports SSML breaks (<break time="1s" />) and emotion markups like [happy], [sad]

### Optional
- **voice_id**: string (default: Ashley) - Preset voice name (Ashley, Dennis, Alex, Darlene) or a custom cloned voice ID
- **speaking_rate**: number (default: 0) - Speaking speed multiplier (0-1.5). 0 = normal speed (1.0)
- **temperature**: number (default: 0) - Randomness control (0-2). 0 uses the model default
- **audio_format**: string (default: mp3) - Output audio format
  Options: mp3, wav, ogg_opus, flac
- **sample_rate**: integer (default: 48000) - Audio sample rate in Hz
  Options: 8000, 16000, 22050, 24000, 32000, 44100, 48000
- **text_normalization**: string (default: auto) - Expand numbers/dates/abbreviations before synthesis
  Options: auto, on, off

## Examples

### Emotion-Marked Assistant Reply
Happy greeting with a precise pause
```json
{
  "model": "inworld/tts-1.5-max",
  "input": {
    "text": "[happy] Welcome back! <break time=\"0.5s\" /> Your order shipped this morning and arrives tomorrow.",
    "voice_id": "Ashley"
  }
}
```

## Response Format
```json
{
  "job_id": "abc123",
  "status": "pending | processing | completed | failed",
  "result": "URL or data (when completed)"
}
```

## Usage Flow
1. POST /predictions with model and input -> receive job_id
2. GET /predictions/{job_id} -> poll until status is completed or failed
3. Result contains output URL(s)

## Tips
- The cheapest premium TTS in the catalog — great default for high-volume voice agents
- Use emotion markups like [happy] at the start of sentences to set the tone
- Insert <break time="0.5s" /> SSML tags for natural pauses
- For natural-language steering instructions, use Realtime TTS 2 instead

## Documentation
https://replicate.com/inworld/tts-1.5-max