---
title: "Inworld TTS 2.0"
description: "Inworld TTS 2.0 on Kuro: Four voices, sixteen languages, tuned for realtime delivery. 2.085 credits per 1,000 characters (≈ $0.05 on Starter)."
canonical_url: "https://meetkuro.com/models/inworld-tts-2/"
locale: "en"
model: "inworld-tts-2"
---

# Inworld TTS 2.0

inworld · Voice · premium

Four voices, sixteen languages, tuned for realtime delivery.

## What it costs

- Per 1,000 characters: 2.085 credits (≈ $0.05)

Dollar figures are approximate, at the Starter plan's rate of $19.00 for 800 credits.

## What it takes

- **Voices**: 4
- **Languages**: 16
- **Text limit**: 2,000 characters

## When to reach for it

The smallest roster in the voice catalog, four voices, across sixteen languages, with a speed control and no emotion selector. It is built for realtime synthesis, and the characteristic that follows from that is responsiveness rather than range.

Four voices is a genuine constraint and the first thing to check against the job. For a single narrator or a two-hander it is enough; for a piece that needs a cast of distinct speakers it is not, and Gemini 3.1 Flash TTS's thirty or Kokoro's thirty-three are the places to go.

Where it earns its premium tier is consistency: a small tuned roster tends to hold character across a long script better than a large one, which matters when narration runs over many separate renders that have to sound like the same person. If the piece is one long voice across a dozen clips, that consistency is worth more than choice.

## How to prompt Inworld TTS 2.0

Describe what you want in your own words and Kuro writes the prompt for you. If you would rather write it yourself, this is what Inworld TTS 2.0 responds to.

Inworld TTS 2.0 is built for realtime synthesis: four preset voices — Ashley (the default), Dennis, Alex and Darlene — across sixteen languages, with a speed control and no emotion selector.

Steer the delivery with bracketed, natural-language cues written inline, in front of the words they shape. Everything else in the text is spoken.

Its small, tuned roster tends to hold a character across a long script better than a large one, which matters when narration runs over many separate renders.

### What it can't do

- At most 2,000 characters per take, the lowest ceiling among Kuro's voice models. Split a longer script first.
- Speed tops out at one and a half times the normal rate.
- No style field and no emotion field.
- Four voices is enough for a narrator or a two-hander, not for a cast of distinct speakers. It also takes custom voices.
- Output is WAV.

### Use something else when…

- You need a cast of many distinct voices: [Gemini 3.1 Flash TTS](https://meetkuro.com/models/gemini-3.1-flash-tts.md).
- A line needs a specific emotional read: [MiniMax Speech 2.8 HD](https://meetkuro.com/models/minimax-speech-2.8-hd.md).

## Inworld TTS 2.0 is one pick in the composer.

Every model in this catalog runs from the same prompt bar, priced in the same credits.

---

## About Kuro

Kuro is an AI picture studio: prompt-driven images, clips, voice-overs and music, and storyboard-backed films with consistent characters across every scene.

Agents connect over MCP and can generate directly:

```
claude mcp add kuro https://api.meetkuro.com/mcp --transport http
```

The app is at https://app.meetkuro.com and requires an account.

Each guide, model page, comparison and free tool page on this site (not a tool's variants, and not the index pages) has a Markdown twin at its own URL plus `.md`, and so do /benchmarks/, the English /agents/ page (as /agents.md) and the MCP tool reference. Model catalog: https://meetkuro.com/models/