# Inworld TTS-2

> Run Inworld TTS-2 by inworld online or via API. $35.00/M chars, no setup.

**URL:** https://inference.sh/apps/inworld/text-to-speech-2
**Last updated:** 2026-05-12

---

Inworld TTS-2 - High-quality multilingual text-to-speech with 100+ languages and natural-language steering

- app: `inworld/text-to-speech-2`
- maker: [inworld](https://inference.sh/apps/inworld.md)
- category: [audio](https://inference.sh/apps/category/audio.md)
- input → output: text → speech
- tasks: [text to speech](https://inference.sh/apps/tag/text-to-speech.md)
- price: $35.00/M chars
- runs via: api, javascript and python sdk, belt cli, mcp

## text-to-speech-2 API Guide

### About
inworld tts-2 - high-quality multilingual text-to-speech with 100+ languages and natural-language steering

### Get an API Key
Create one in [settings → api keys](https://app.inference.sh/settings/keys). The examples read it from `INFERENCE_API_KEY`.

```bash
export INFERENCE_API_KEY="inf_your_key"
```

### 1. Calling the API

#### Install the Client

```bash
pip install inferencesh
```

#### Run and Get Result
Submit a request and wait for the final result.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @5vh6r16n pinned
result = client.run({
        "app": "inworld/text-to-speech-2@5vh6r16n",
        "input": {
            "text": "text"
        }
    })

print(result["output"])
```

#### Stream Live Updates
Get real-time progress updates as the task runs.

```python
import os
from inferencesh import inference

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## version @5vh6r16n pinned
## stream=True yields updates as they arrive
for update in client.run({
        "app": "inworld/text-to-speech-2@5vh6r16n",
        "input": {
            "text": "text"
        }
    }, stream=True):
    if update.get("progress"):
        print(f"progress: {update['progress']}%")
    if update.get("output"):
        print(f"output: {update['output']}")
```

#### Run in the Background
Start the task and get its id back right away, then check on it with `GET /tasks/{id}`. It is done when `status` is 10 (completed), 11 (failed) or 12 (cancelled).

```python
import os
from inferencesh import inference, TaskStatus

client = inference(api_key=os.environ["INFERENCE_API_KEY"])

## returns as soon as the task is created
task = client.run({
        "app": "inworld/text-to-speech-2@5vh6r16n",
        "input": {
            "text": "text"
        }
    }, wait=False)

## later: read its current state
state = client.tasks.get(task["id"]).data
if state["status"] == TaskStatus.COMPLETED:
    print(state["output"])
```

### 2. Files

#### Automatic Upload

```python
## local file paths are automatically uploaded
result = client.run({
    "app": "inworld/text-to-speech-2@5vh6r16n",
    "input": {
        "image": "/path/to/local/image.png",  # detected & uploaded
        "audio": "https://example.com/audio.mp3",  # url passed through
    }
})
```

#### Manual Upload

```python
## upload and get a hosted URL
file = client.files.upload("/path/to/file.png")
print(file.uri)  # https://cloud.inference.sh/...
```

### 3. Schema

#### Input
- **text** (string) *required*: Text to convert to speech (max 2,000 characters). Use [brackets] for steering: emotion, volume, speed, non-verbals like [laugh] or [sigh].
- **voice_id** (string): Voice ID — built-in (e.g. Sarah, Alex, Ashley, Dennis, Hana, Blake, Luna, Clive) or custom cloned/designed voice ID. 271+ built-in voices across 15 languages.
- **language** (string): BCP-47 language tag (e.g. 'en-US', 'fr-FR', 'ja-JP'). Auto-detected if omitted. 100+ languages supported.
- **delivery_mode** (string): Controls voice performance style. STABLE = consistent, BALANCED = natural, CREATIVE = expressive.
- **audio_encoding** (string): Audio output format.
- **sample_rate_hertz** (integer): Audio sample rate in Hz. Supported: 8000, 16000, 22050, 24000, 32000, 44100, 48000.
- **speaking_rate** (number): Speaking rate multiplier (0.5-1.5).

#### Output
- **audio** (string): Generated speech audio file

## other audio apps

- [Pika H3 Flex Audio Stems](https://inference.sh/apps/pika/pika-h3-flex-audio-stems.md): $0.001/stem-sec (3 stems: dialogue, music, effect)
- [Fish Audio Drama 3](https://inference.sh/apps/fish-audio/drama-3.md): $50.00/1M UTF-8 bytes
- [Eleven Flash v2.5](https://inference.sh/apps/elevenlabs/eleven-flash-v2-5.md): $0.04/1K characters
- [Eleven Multilingual v2](https://inference.sh/apps/elevenlabs/eleven-multilingual-v2.md): $0.08/1K characters
- [Eleven v3](https://inference.sh/apps/elevenlabs/eleven-v3.md): $0.08/1K characters

## faq

### how much does Inworld TTS-2 cost?

$35.00/M chars. you pay per run from your inference shell credits. no subscription is required.

### how do I run Inworld TTS-2 via api?

call inworld/text-to-speech-2 with the javascript or python sdk, the rest api, or `belt app run inworld/text-to-speech-2` from a terminal. the api reference on this page lists every input.

### who makes Inworld TTS-2?

Inworld TTS-2 is made by inworld and runs on inference shell. every inworld app is listed at https://inference.sh/apps/inworld.

### can my agent use Inworld TTS-2?

yes. agents call it as a tool through the inference shell mcp server (https://api.inference.sh/mcp), the belt cli or the sdk, and pay per run like you do.

### what are the alternatives to Inworld TTS-2?

other audio apps on inference shell include Pika H3 Flex Audio Stems, Fish Audio Drama 3, Eleven Flash v2.5, Eleven Multilingual v2. they run through the same api, so switching is a one-line change.