TTS 1.5 Max
Model Information
Display Name: TTS 1.5 Max
API Model ID: inworld/tts-1.5-max
Category: Text To Audio
Description: Inworld TTS 1.5 Max is a high-quality text-to-speech model ranked #1 on Artificial Analysis, with <200ms latency and support for 15 languages including Portuguese. ## Quick Start Send text and receive natural speech audio: ```json { "text": "Olá! Como posso ajudar você hoje?", "voice_id": "Ashley", "output_format": "mp3" } ``` ## Available Voices | Voice | Description | |-------|-------------| | **Ashley** | Warm, friendly female voice | | **Dennis** | Calm, professional male voice | | **Alex** | Energetic, dynamic male voice | | **Darlene** | Soothing Southern female voice | ## Supported Languages English, Portuguese, Spanish, French, German, Italian, Chinese, Japanese, Korean, Russian, Polish, Dutch, Hindi, Hebrew, Arabic ## Text Markup (Emotions & Effects) Add expressiveness to your speech: **Emotions:** ``` [happy] Que ótimo falar com você! [sad] Sinto muito por isso. [angry] Isso é inaceitável! [surprised] Uau, não esperava isso! ``` **Non-verbal Sounds:** ``` [laugh] Isso foi muito engraçado! [sigh] Bem, vamos tentar de novo. [cough] Desculpe... onde estávamos? ``` **Pauses:** ``` Primeiro ponto. <break time="1s" /> Segundo ponto. ``` ## Output Formats MP3, WAV, OGG Opus, FLAC ## Pricing - **Per 1000 characters**: Text processing cost - **Per minute**: Audio duration cost
How to Use This Model
To use TTS 1.5 Max via the HInow.ai API, use the model ID: inworld/tts-1.5-max
API Request Example (Chat/Text)
POST https://api.hinow.ai/v1/chat/completions
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
{
"model": "inworld/tts-1.5-max",
"messages": [
{"role": "user", "content": "Your message here"}
]
}
Pricing
- per_1000_chars: $0.014
- per_minute: $0.008
Available Parameters
- voice_gender: Gender of the voice (Options: female, male)
- voice_id: Specific voice to use (Female: Ashley, Darlene | Male: Dennis, Alex) (Options: Ashley, Darlene, Dennis, Alex)
- output_format: Audio output format (Options: mp3, wav, ogg, flac)
- language: Language for text-to-speech synthesis (Options: English, Portuguese, Spanish, French, German, Italian, Chinese, Japanese, Korean, Russian, Polish, Dutch, Hindi, Hebrew, Arabic)
Quick Reference
To use this model, set: "model": "inworld/tts-1.5-max"
Featured: Yes
Documentation: https://hinow.ai/models/inworld/tts-1.5-max
API Endpoint: https://api.hinow.ai/v1
