# Text to Speech Generation

## Convert Text into Speech

The text-to-speech feature enables you to convert written text into spoken audio with a selection of voices and languages. You can seamlessly integrate this audio into a clip by specifying the desired voice and the text to be spoken.

```json
{
    "asset": {
        "type": "text-to-speech",
        "text": "Good evening, in Sydney tonight we’re tracking a developing story as unexpected storms roll in across the city, bringing with them flash flooding warnings and major disruptions to the evening commute.",
        "voice": "Amy"
    },
    "start": 0,
    "length": "auto"
}
```

This request will embed the generated speech at the beginning of your video, with the duration automatically matching the length of the generated audio. For more details on optimizing timing, refer to [smart clips](/docs/guide/architecting-an-application/smart-clips).

### Translating text

To create an audio file in a different language, use the `language` option. Ensure that you select a `voice` compatible with the desired `language`. 

```json
{
    "asset": {
        "type": "text-to-speech",
        "text": "Good evening, in Sydney tonight we’re tracking a developing story as unexpected storms roll in across the city, bringing with them flash flooding warnings and major disruptions to the evening commute.",
        "voice": "Seoyeon",
        "language": "ko-KR"
    },
    "start": 0,
    "length": "auto"
}
```

The above example creates an audio file in Korean. The English text is translated to and spoken in Korean.

#### Supported translations

| Language | Value |
|----------|-------|
| Chinese (Mandarin) | cmn-CN |
| Danish | da-DK |
| German | de-DE |
| English (Australian) | en-AU |
| English (British) | en-GB |
| English (Indian) | en-IN |
| English (US) | en-US |
| Spanish (European) | es-ES |
| Spanish (Mexican) | es-MX |
| Spanish (US) | es-US |
| French (Canadian) | fr-CA |
| French | fr-FR |
| Italian | it-IT |
| Japanese | ja-JP |
| Hindi | hi-IN |
| Korean | ko-KR |
| Norwegian Bokmål | nb-NO |
| Dutch | nl-NL |
| Polish | pl-PL |
| Portuguese (Brazilian) | pt-BR |
| Portuguese (European) | pt-PT |
| Swedish | sv-SE |
| English (New Zealand) | en-NZ |
| English (South African) | en-ZA |
| Catalan | ca-ES |
| German (Austrian) | de-AT |
| Chinese (Cantonese) | yue-CN |
| Arabic (Gulf) | ar-AE |
| Finnish | fi-FI |

### Newscaster mode

Shotstack’s text-to-speech service includes a `newscaster` mode, which produces audio that emulates a newsreader’s delivery. To enable this mode, set the `newscaster` option to `true`.

```json
{
    "asset": {
        "type": "text-to-speech",
        "text": "Good evening, in Sydney tonight we’re tracking a developing story as unexpected storms roll in across the city, bringing with them flash flooding warnings and major disruptions to the evening commute.",
        "voice": "Joanna",
        "newscaster": true
    },
    "start": 0,
    "length": "auto"
}
```

The `newscaster` style is available with the `Matthew` and `Joanna` voices in US English, the `Lupe` voice in US Spanish, and the `Amy` voice in British English.

### Voices

The Shotstack text-to-speech service offers a variety of voices in different languages and genders:

| Voice Name | Language | Gender |
|------------|----------|--------|
| Hala | Arabic (Gulf) | Female |
| Lisa | Dutch (Belgian) | Female |
| Arlet | Catalan | Female |
| Hiujin | Chinese (Cantonese) | Female |
| Zhiyu | Chinese (Mandarin) | Female |
| Sofie | Danish | Female |
| Laura | Dutch | Female |
| Olivia | English (Australian) | Female |
| Amy | English (British) | Female |
| Emma | English (British) | Female |
| Brian | English (British) | Male |
| Arthur | English (British) | Male |
| Kajal | English (Indian) | Female |
| Niamh | English (Ireland) | Female |
| Aria | English (New Zealand) | Female |
| Ayanda | English (South African) | Female |
| Ivy | English (US) | Female (child) |
| Joanna | English (US) | Female |
| Kendra | English (US) | Female |
| Kimberly | English (US) | Female |
| Salli | English (US) | Female |
| Joey | English (US) | Male |
| Justin | English (US) | Male (child) |
| Kevin | English (US) | Male (child) |
| Matthew | English (US) | Male |
| Ruth | English (US) | Female |
| Stephen | English (US) | Male |
| Suvi | Finnish | Female |
| Léa | French | Female |
| Rémi | French | Male |
| Gabrielle | French (Canadian) | Female |
| Liam | French (Canadian) | Male |
| Vicki | German | Female |
| Daniel | German | Male |
| Hannah | German (Austrian) | Female |
| Bianca | Italian | Female |
| Adriano | Italian | Male |
| Takumi | Japanese | Male |
| Kazuha | Japanese | Female |
| Tomoko | Japanese | Female |
| Seoyeon | Korean | Female |
| Ida | Norwegian | Female |
| Ola | Polish | Female |
| Camila | Portuguese (Brazilian) | Female |
| Vitória/Vitoria | Portuguese (Brazilian) | Female |
| Thiago | Portuguese (Brazilian) | Male |
| Inês/Ines | Portuguese (European) | Female |
| Lucia | Spanish (European) | Female |
| Sergio | Spanish (European) | Male |
| Mia | Spanish (Mexican) | Female |
| Andrés | Spanish (Mexican) | Male |
| Lupe | Spanish (US) | Female |
| Pedro | Spanish (US) | Male |
| Elin | Swedish | Female |

## ElevenLabs Integration

Our ElevenLabs integration is currently unavailable.

:::danger Warning

Generated AI assets in the sandbox environment will incur credits.

:::