Inworld Inworld 1.5 Mini Text To Speech

Inworld Inworld 1.5 Mini Text To Speech

Playground

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

Features

Inworld 1.5 Mini Text-to-Speech

Inworld 1.5 Mini is a lightweight, ultra-affordable text-to-speech model that converts written text into natural speech. It offers the same voice selection, speaking rate, and expressiveness controls as the Max model — at half the cost. Perfect for high-volume workflows, prototyping, and budget-conscious production.

• Need higher quality? Try Inworld 1.5 Max Text-to-Speech

Why Choose This?

• Ultra-low cost Just $0.005 per 1,000 characters — the most affordable option for text-to-speech at scale.

• Multilingual voice library 65+ voices across 14 languages including English, Chinese, Japanese, Korean, and more.

• 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 delivery; higher values for more dynamic, varied speech.

• Fast processing Lightweight architecture delivers quick turnaround, ideal for real-time or high-volume pipelines.

Parameters

Available Voices

English

Chinese

Japanese

Korean

French

German

Spanish

Portuguese

Italian

Dutch

Polish

Russian

Hindi

Hebrew

Arabic

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: $0.005 per 1,000 characters
• Rounding: character count is rounded up to the next 1,000

Best Use Cases

• High-Volume Production — Generate large batches of audio at minimal cost.
• Prototyping & Testing — Quickly preview voiceovers before committing to final production.
• Chatbots & Virtual Assistants — Add voice output to conversational AI at scale.
• Content Accessibility — Convert written content to audio affordably for wider audiences.
• Game & App Dialogue — Generate character voice lines for interactive experiences on a budget.
• Multilingual Content — Create audio content in 14 languages from a single API.

Pro Tips

• Use Mini for drafting and iteration, then switch to Max for final production if higher quality is needed.
• Keep speaking_rate around 1 for natural pacing; adjust lower for dramatic reads, higher for quick announcements.
• Lower temperature gives more predictable, consistent output — great for automated systems.
• Break long texts into logical paragraphs for better pacing and natural pauses.
• Match voice language to your text language for best pronunciation and intonation.

Notes

• Text is the only required field.
• Billing is based on character count, rounded up to the nearest 1,000.
• For maximum voice quality, consider Inworld 1.5 Max.

Related Models

• Inworld 1.5 Max Text-to-Speech — Higher quality voices at $0.01 per 1,000 characters.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/inworld/inworld-1.5-mini/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}"