Inworld 1.5 Max Text To Speech

Inworld 1.5 Max Text To Speech

Playground

Inworld 1.5 Max delivers premium text-to-speech synthesis with 56+ multilingual voices, adjustable speaking rate, and high-fidelity natural-sounding audio output. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Inworld 1.5 Max Text-to-Speech

Inworld 1.5 Max is a high-quality text-to-speech model that converts written text into natural, expressive speech. Choose from a variety of voice presets, fine-tune speaking rate and expressiveness with simple controls, and generate professional-grade audio in seconds — ideal for IVR systems, voiceovers, content creation, and accessibility.

Why Choose This?

• Natural-sounding voices Multiple voice presets with realistic intonation, pacing, and emotion for lifelike speech output.

• Voice selection Choose from a library of distinct voice identities to match your brand, character, or use case.

• Speaking rate control Adjust the speed of speech to suit narration, dialogue, announcements, or any delivery style.

• Temperature control Fine-tune expressiveness — lower values for consistent, predictable delivery; higher values for more dynamic, varied speech.

• Ultra-low cost Just $0.01 per 1,000 characters — affordable even at scale.

Parameters

How to Use

1. Enter your text — type or paste the content you want converted to speech.
2. Select a voice — choose a voice preset from the voice_id dropdown.
3. Adjust speaking rate — slide to control how fast or slow the speech is delivered.
4. Adjust temperature — slide to control the expressiveness and variation in delivery.
5. Run — submit and download the generated audio.

Pricing

Billing Rules

• Rate: $0.01 per 1,000 characters
• Rounding: character count is rounded up to the next 1,000

Best Use Cases

• IVR & Phone Systems — Generate professional call menus, hold messages, and automated responses.
• Video Voiceovers — Add narration to marketing videos, tutorials, and presentations.
• Content Creation — Convert blog posts, articles, or scripts into audio for podcasts and social media.
• Accessibility — Provide audio versions of written content for visually impaired users.
• Game & App Dialogue — Create character voices for interactive experiences and virtual assistants.

Pro Tips

• Keep speaking_rate around 1 for natural-sounding narration; lower for dramatic reads, higher for fast announcements.
• Use lower temperature for consistent, predictable voiceovers (e.g., IVR); higher temperature for more expressive character dialogue.
• Break long texts into logical paragraphs for better pacing and natural pauses.
• Test different voice_id options to find the best match for your brand or character.

Notes

• Text is the only required field.
• Billing is based on character count, rounded up to the nearest 1,000.
• Very long texts may take slightly longer to process.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/inworld/1.5-max/text-to-speech" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "voice_id": "Alex",
    "speaking_rate": 1,
    "temperature": 1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"