---
title: Inworld Realtime TTS-2 | Runware Docs
url: https://runware.ai/docs/models/inworld-tts-2
description: Conversational text-to-speech with realtime voice direction and audio-aware delivery
---
# Inworld Realtime TTS-2

Inworld Realtime TTS-2 is a conversational text-to-speech model built for realtime voice interaction rather than static narration. It supports free-form voice direction, carries tone and pacing forward from prior audio in a session, preserves one voice identity across 100+ languages, and is designed for expressive, low-latency speech in assistants, characters, support agents, and interactive products.

- **ID**: `inworld:tts@2`
- **Status**: live
- **Creator**: Inworld AI
- **Release Date**: May 5, 2026
- **Capabilities**: Text to Audio

## Compatibility & Validation

When `speech.language` is `en`, `speech.voice` is limited to `Loretta`, `Darlene`, `Marlene`, `Hank`, `Evelyn`, `Celeste`, `Pippa`, `Tessa`, `Liam`, `Callum`, `Hamish`, `Abby`, `Graham`, `Rupert`, `Mortimer`, `Snik`, `Anjali`, `Saanvi`, `Arjun`, `Claire`, `Oliver`, `Simon`, `Elliot`, `James`, `Serena`, `Gareth`, `Vinny`, `Lauren`, `Jessica`, `Ethan`, `Tyler`, `Jason`, `Chloe`, `Veronica`, `Victoria`, `Miranda`, `Sebastian`, `Victor`, `Malcolm`, `Nate`, `Brian`, `Amina`, `Kelsey`, `Derek`, `Evan`, `Kayla`, `Jake`, `Grant`, `Tristan`, `Nadia`, `Selene`, `Marcus`, `Riley`, `Damon`, `Cedric`, `Mia`, `Naomi`, `Jonah`, `Levi`, `Avery`, `Brandon`, `Conrad`, `Bianca`, `Lucian`, `Trevor`, `Alex`, `Ashley`, `Craig`, `Deborah`, `Dennis`, `Edward`, `Elizabeth`, `Hades`, `Julia`, `Pixie`, `Mark`, `Olivia`, `Priya`, `Ronald`, `Sarah`, `Shaun`, `Theodore`, `Timothy`, `Wendy`, `Dominus`, `Hana`, `Clive`, `Carter`, `Blake`, `Luna`, `Reed`, `Duncan`, `Felix`, `Eleanor`, `Sophie`.

---

When `speech.language` is `ja`, `speech.voice` is limited to `Asuka`, `Satoshi`.

---

When `speech.language` is `zh`, `speech.voice` is limited to `Yichen`, `Xiaoyin`, `Xinyi`, `Jing`.

---

When `speech.language` is `ko`, `speech.voice` is limited to `Hyunwoo`, `Minji`, `Seojun`, `Yoona`.

---

When `speech.language` is `ru`, `speech.voice` is limited to `Svetlana`, `Elena`, `Dmitry`, `Nikolai`.

---

When `speech.language` is `it`, `speech.voice` is limited to `Gianni`, `Orietta`.

---

When `speech.language` is `es`, `speech.voice` is limited to `Diego`, `Lupita`, `Miguel`, `Rafael`.

---

When `speech.language` is `de`, `speech.voice` is limited to `Johanna`, `Josef`.

---

When `speech.language` is `fr`, `speech.voice` is limited to `Alain`, `Hélène`, `Mathieu`, `Étienne`.

---

When `speech.language` is `ar`, `speech.voice` is limited to `Nour`, `Omar`.

---

When `speech.language` is `pl`, `speech.voice` is limited to `Szymon`, `Wojciech`.

---

When `speech.language` is `nl`, `speech.voice` is limited to `Erik`, `Katrien`, `Lennart`, `Lore`.

---

When `speech.language` is `hi`, `speech.voice` is limited to `Riya`, `Manoj`.

---

When `speech.language` is `he`, `speech.voice` is limited to `Yael`, `Oren`.

## Request Parameters

**API Options**

Platform-level options for task execution and delivery.

### [taskType](https://runware.ai/docs/models/inworld-tts-2#request-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Identifier for the type of task being performed

### [taskUUID](https://runware.ai/docs/models/inworld-tts-2#request-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

### [outputType](https://runware.ai/docs/models/inworld-tts-2#request-outputtype)

- **Type**: `string`
- **Default**: `URL`

Audio output type.

**Allowed values**: `URL` `base64Data` `dataURI`

### [outputFormat](https://runware.ai/docs/models/inworld-tts-2#request-outputformat)

- **Type**: `string`
- **Default**: `MP3`

Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities.

- \`MP3\`: Compressed audio, smaller file size.
- \`WAV\`: Uncompressed, high-quality audio.
- \`FLAC\`: Lossless compression.
- \`OGG\`: Open-source compressed audio format (Vorbis codec).

**Allowed values**: `MP3` `WAV` `FLAC` `OGG`

### [audioSettings](https://runware.ai/docs/models/inworld-tts-2#request-audiosettings)

- **Path**: `audioSettings.bitrate`
- **Type**: `object (3 properties)`

Audio encoding settings for controlling the bitrate, number of channels, and sample rate of the generated audio. Only applicable for lossy output formats (`MP3` and `OGG`). When using lossless formats (`WAV` or `FLAC`), this parameter must not be provided.

The available sample rates and valid bitrate ranges depend on the output format. For `OGG`, bitrate limits also vary by the number of channels.

**MP3 bitrate limits**:

Bitrate limits for MP3 are the same regardless of mono or stereo.

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 64 kbps |
| 11,025 Hz | 8 kbps | 64 kbps |
| 12,000 Hz | 8 kbps | 64 kbps |
| 16,000 Hz | 8 kbps | 160 kbps |
| 22,050 Hz | 8 kbps | 160 kbps |
| 24,000 Hz | 8 kbps | 160 kbps |
| 32,000 Hz | 32 kbps | 320 kbps |
| 44,100 Hz | 32 kbps | 320 kbps |
| 48,000 Hz | 32 kbps | 320 kbps |

**OGG bitrate limits — Mono (1 channel)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 8 kbps | 40 kbps |
| 12,000 Hz | 16 kbps | 48 kbps |
| 16,000 Hz | 16 kbps | 96 kbps |
| 24,000 Hz | 16 kbps | 80 kbps |
| 48,000 Hz | 32 kbps | 224 kbps |

**OGG bitrate limits — Stereo (2 channels)**:

| Sample Rate | Min Bitrate | Max Bitrate |
| --- | --- | --- |
| 8,000 Hz | 16 kbps | 80 kbps |
| 12,000 Hz | 16 kbps | 96 kbps |
| 16,000 Hz | 24 kbps | 192 kbps |
| 24,000 Hz | 32 kbps | 160 kbps |
| 48,000 Hz | 48 kbps | 256 kbps |

> [!NOTE]
> **Lossless formats**: When `outputFormat` is set to `WAV` or `FLAC`, the `audioSettings` parameter is not available since these formats produce uncompressed or lossless audio with no configurable encoding settings.

#### [bitrate](https://runware.ai/docs/models/inworld-tts-2#request-audiosettings-bitrate)

- **Path**: `audioSettings.bitrate`
- **Type**: `integer`
- **Min**: `8`

Audio bitrate in kbps.

#### [channels](https://runware.ai/docs/models/inworld-tts-2#request-audiosettings-channels)

- **Path**: `audioSettings.channels`
- **Type**: `integer`
- **Default**: `2`

Number of audio channels. 1 for mono, 2 for stereo.

**Allowed values**: `1` `2`

#### [sampleRate](https://runware.ai/docs/models/inworld-tts-2#request-audiosettings-samplerate)

- **Path**: `audioSettings.sampleRate`
- **Type**: `integer`

Audio sample rate in Hz.

### [webhookURL](https://runware.ai/docs/models/inworld-tts-2#request-webhookurl)

- **Type**: `string`
- **Format**: `URI`

Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available.

**Learn more** (1 resource):

- [Webhooks](https://runware.ai/docs/platform/webhooks) (platform)

### [deliveryMethod](https://runware.ai/docs/models/inworld-tts-2#request-deliverymethod)

- **Type**: `string`
- **Default**: `sync`

Determines how the API delivers task results.

**Allowed values**:

- `sync` Returns complete results directly in the API response.
- `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

**Learn more** (1 resource):

- [Task Polling](https://runware.ai/docs/platform/task-polling) (platform)

### [uploadEndpoint](https://runware.ai/docs/models/inworld-tts-2#request-uploadendpoint)

- **Type**: `string`
- **Format**: `URI`

Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials.

**Common use cases:**

- **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs.
- **CDN integration**: Upload to content delivery networks for immediate distribution.

```text
// S3 presigned URL for secure upload
https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600

// Google Cloud Storage presigned URL
https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789

// Custom storage endpoint
https://storage.example.com/uploads/generated-image.jpg
```

The content data will be sent as the request body to the specified URL when generation is complete.

### [ttl](https://runware.ai/docs/models/inworld-tts-2#request-ttl)

- **Type**: `integer`
- **Min**: `60`

Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`.

### [includeCost](https://runware.ai/docs/models/inworld-tts-2#request-includecost)

- **Type**: `boolean`
- **Default**: `false`

Include task cost in the response.

### [numberResults](https://runware.ai/docs/models/inworld-tts-2#request-numberresults)

- **Type**: `integer`
- **Min**: `1`
- **Max**: `4`
- **Default**: `1`

Number of results to generate. Each result uses a different seed, producing variations of the same parameters.

**Generation Parameters**

Core parameters for controlling the generated content.

### [model](https://runware.ai/docs/models/inworld-tts-2#request-model)

- **Type**: `string`
- **Required**: true
- **Value**: `inworld:tts@2`

Identifier of the model to use for generation.

### [speech](https://runware.ai/docs/models/inworld-tts-2#request-speech)

- **Path**: `speech.text`
- **Type**: `object (4 properties)`
- **Required**: true

Settings for speech generation.

#### [text](https://runware.ai/docs/models/inworld-tts-2#request-speech-text)

- **Path**: `speech.text`
- **Type**: `string`
- **Required**: true
- **Min**: `2`
- **Max**: `2000`

Text to convert to speech.

#### [voice](https://runware.ai/docs/models/inworld-tts-2#request-speech-voice)

- **Path**: `speech.voice`
- **Type**: `string`
- **Required**: true

Voice identifier from the Inworld voice library.

**Allowed values**: `Loretta` `Darlene` `Marlene` `Hank` `Evelyn` `Celeste` `Pippa` `Tessa` `Liam` `Callum` `Hamish` `Abby` `Graham` `Rupert` `Mortimer` `Snik` `Anjali` `Saanvi` `Arjun` `Claire` `Oliver` `Simon` `Elliot` `James` `Serena` `Gareth` `Vinny` `Lauren` `Jessica` `Ethan` `Tyler` `Jason` `Chloe` `Veronica` `Victoria` `Miranda` `Sebastian` `Victor` `Malcolm` `Nate` `Brian` `Amina` `Kelsey` `Derek` `Evan` `Kayla` `Jake` `Grant` `Tristan` `Nadia` `Selene` `Marcus` `Riley` `Damon` `Cedric` `Mia` `Naomi` `Jonah` `Levi` `Avery` `Brandon` `Conrad` `Bianca` `Lucian` `Trevor` `Alex` `Ashley` `Craig` `Deborah` `Dennis` `Edward` `Elizabeth` `Hades` `Julia` `Pixie` `Mark` `Olivia` `Priya` `Ronald` `Sarah` `Shaun` `Theodore` `Timothy` `Wendy` `Dominus` `Hana` `Clive` `Carter` `Blake` `Luna` `Reed` `Duncan` `Felix` `Eleanor` `Sophie` `Asuka` `Satoshi` `Yichen` `Xiaoyin` `Xinyi` `Jing` `Hyunwoo` `Minji` `Seojun` `Yoona` `Svetlana` `Elena` `Dmitry` `Nikolai` `Gianni` `Orietta` `Diego` `Lupita` `Miguel` `Rafael` `Johanna` `Josef` `Alain` `Hélène` `Mathieu` `Étienne` `Nour` `Omar` `Szymon` `Wojciech` `Erik` `Katrien` `Lennart` `Lore` `Riya` `Manoj` `Yael` `Oren`

#### [language](https://runware.ai/docs/models/inworld-tts-2#request-speech-language)

- **Path**: `speech.language`
- **Type**: `string`
- **Min**: `1`

Language code for speech generation.

**Allowed values**: `en` `ja` `zh` `ko` `ru` `it` `es` `de` `fr` `ar` `pl` `nl` `hi` `he`

#### [speed](https://runware.ai/docs/models/inworld-tts-2#request-speech-speed)

- **Path**: `speech.speed`
- **Type**: `float`
- **Min**: `0.5`
- **Max**: `1.5`
- **Step**: `0.1`
- **Default**: `1`

Playback speed of the generated speech.

**Settings**

Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object.

### [textNormalization](https://runware.ai/docs/models/inworld-tts-2#request-settings-textnormalization)

- **Path**: `settings.textNormalization`
- **Type**: `boolean`

Expands numbers, dates, abbreviations before speech generation.

## Response Parameters

### [taskType](https://runware.ai/docs/models/inworld-tts-2#response-tasktype)

- **Type**: `string`
- **Required**: true
- **Value**: `audioInference`

Type of the task.

### [taskUUID](https://runware.ai/docs/models/inworld-tts-2#response-taskuuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the task.

### [audioUUID](https://runware.ai/docs/models/inworld-tts-2#response-audiouuid)

- **Type**: `string`
- **Required**: true
- **Format**: `UUID v4`

UUID of the output audio.

### [audioURL](https://runware.ai/docs/models/inworld-tts-2#response-audiourl)

- **Type**: `string`
- **Format**: `URI`

URL of the output audio.

### [audioBase64Data](https://runware.ai/docs/models/inworld-tts-2#response-audiobase64data)

- **Type**: `string`

Base64-encoded audio data.

### [audioDataURI](https://runware.ai/docs/models/inworld-tts-2#response-audiodatauri)

- **Type**: `string`
- **Format**: `URI`

Data URI of the output audio.

### [seed](https://runware.ai/docs/models/inworld-tts-2#response-seed)

- **Type**: `integer`

The seed used for generation. If none was provided, shows the randomly generated seed.

### [cost](https://runware.ai/docs/models/inworld-tts-2#response-cost)

- **Type**: `float`

Task cost in USD. Present when `includeCost` is set to `true` in the request.

## Examples

### Floating Archive Welcome Message (Text to Audio)

**Request**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "a4a20469-3a41-4288-bde0-478f8874dcec",
  "model": "inworld:tts@2",
  "speech": {
    "text": "ようこそ、漂う書庫へ。私は案内役です。ここでは、失われた手紙、航路の記録、そして誰にも届けられなかった物語を保管しています。はじめての方ですね。緊張しなくて大丈夫。まずは深呼吸をひとつ。それから、今いちばん知りたいことを教えてください。静かな案内が必要なら、ゆっくりお手伝いします。",
    "voice": "Asuka",
    "language": "ja",
    "speed": 0.9
  },
  "settings": {
    "textNormalization": true
  }
}
```

**Response**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "a4a20469-3a41-4288-bde0-478f8874dcec",
  "audioUUID": "fefeebd4-0980-4a98-9c33-ea3f4b9c323c",
  "audioURL": "https://am.runware.ai/audio/os/a09dlim3/ws/5/ai/fefeebd4-0980-4a98-9c33-ea3f4b9c323c.mp3",
  "cost": 0.004935
}
```

---

### Subterranean Transit Delay Announcement (Text to Audio)

**Request**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "a3266d2e-f9fa-49c0-a851-ad8ff96bebb4",
  "model": "inworld:tts@2",
  "speech": {
    "text": "Attention passengers on Platform 4: the eastbound train is delayed by approximately twelve minutes due to signal maintenance ahead. If you need to reach Central Exchange sooner, please transfer to the silver line at Junction Square and follow the overhead signs for Track B. We know delays are frustrating, and we appreciate your patience. Staff in blue jackets are available near the information pillars if you need step-by-step directions.",
    "voice": "Claire",
    "language": "en",
    "speed": 0.9
  },
  "settings": {
    "textNormalization": true
  }
}
```

**Response**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "a3266d2e-f9fa-49c0-a851-ad8ff96bebb4",
  "audioUUID": "614e4013-20fc-4ade-9bdc-c4247079fa1b",
  "audioURL": "https://am.runware.ai/audio/os/a08dlim3/ws/5/ai/614e4013-20fc-4ade-9bdc-c4247079fa1b.mp3",
  "cost": 0.015435
}
```

---

### Harbor Emergency Siren Bulletin (Text to Audio)

**Request**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "1540ed6f-d187-4238-93be-e52499e94e66",
  "model": "inworld:tts@2",
  "speech": {
    "text": "Attention all crews at Breakwater Terminal 7. This is a safety bulletin for 04/18/2027, issued at 05:45. Due to a pressure fault in storage unit B-12, access to piers 3 through 5 is restricted within a 200 meter radius. Tug 28 and response team 14 are en route, with arrival in 6 minutes. Personnel assigned to zone C should report to muster point 2 by 06:00 and confirm headcount of 47. If you are carrying class 8 materials, contact dispatch on channel 16 immediately and state your cargo ID.",
    "voice": "Gareth",
    "language": "en",
    "speed": 1
  },
  "settings": {
    "textNormalization": true
  }
}
```

**Response**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "1540ed6f-d187-4238-93be-e52499e94e66",
  "audioUUID": "817e9e9c-aaab-4f04-b8ca-17f8abce0e56",
  "audioURL": "https://am.runware.ai/audio/os/a09dlim3/ws/5/ai/817e9e9c-aaab-4f04-b8ca-17f8abce0e56.mp3",
  "cost": 0.01729
}
```

---

### Orbital Docking Concierge Briefing (Text to Audio)

**Request**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "4e4053b1-919c-464a-8579-12329177adb7",
  "model": "inworld:tts@2",
  "speech": {
    "text": "Welcome to Meridian Transfer Ring. Docking in four minutes. Please secure loose items, confirm your berth number on the panel to your left, and keep the central passage clear for incoming crew. If this is your first time rotating through partial gravity, take a slow breath and let your balance adjust before standing. Connecting departures to Europa freight, inner-orbit commuter lines, and the museum shuttle will begin boarding twenty minutes after arrival. And for passengers meeting family at Gate C, yes, they can see you wave through the glass.",
    "voice": "Claire",
    "language": "en",
    "speed": 0.9
  },
  "settings": {
    "textNormalization": true
  }
}
```

**Response**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "4e4053b1-919c-464a-8579-12329177adb7",
  "audioUUID": "aba7608a-1f6c-4a20-b66e-9f67d8839309",
  "audioURL": "https://am.runware.ai/audio/os/a07dlim3/ws/5/ai/aba7608a-1f6c-4a20-b66e-9f67d8839309.mp3",
  "cost": 0.019285
}
```

---

### Desert Relay Station Dispatch (Text to Audio)

**Request**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "1574f33e-8fa1-4fa1-a45a-1b385a048ad0",
  "model": "inworld:tts@2",
  "speech": {
    "text": "Central de relevo Sierra Nueve, atención. Si escuchan este mensaje, mantengan la calma. Hemos recuperado energía parcial en el anillo exterior y el sistema de enfriamiento vuelve a responder, pero el corredor norte sigue bloqueado por polvo y escombros. Prioridad uno: personal médico al módulo dos. Prioridad dos: equipo técnico con filtros nuevos a la compuerta este. No corran, no saturen el canal y confirmen su ubicación al llegar. Repito: la situación está contenida, pero necesitamos movimientos precisos y ordenados. En diez minutos emitiré una nueva actualización.",
    "voice": "Diego",
    "language": "es",
    "speed": 1
  },
  "settings": {
    "textNormalization": true
  }
}
```

**Response**:

```json
{
  "taskType": "audioInference",
  "taskUUID": "1574f33e-8fa1-4fa1-a45a-1b385a048ad0",
  "audioUUID": "ef92a38b-c3e8-44ca-86f0-d916c3f7283e",
  "audioURL": "https://am.runware.ai/audio/os/a05d22/ws/5/ai/ef92a38b-c3e8-44ca-86f0-d916c3f7283e.mp3",
  "cost": 0.020055
}
```