Voice design

POST

/v1/text-to-voice/create-previews

Create a voice from a text prompt.

output_formatenumOptionalDefaults to mp3_44100_192

The output format of the generated audio.

This endpoint expects an object.

voice_descriptionstringRequired>=20 characters<=1000 characters

Description to use for the created voice.

textstringRequired>=100 characters<=1000 characters

Text to generate, text length has to be between 100 and 1000.

auto_generate_textbooleanOptionalDefaults to false

Whether to automatically generate a text suitable for the voice description.

Successful Response

previewslist of objects

textstring

1	curl -X POST https://api.elevenlabs.io/v1/text-to-voice/create-previews \
2	-H "xi-api-key: <apiKey>" \
3	-H "Content-Type: application/json" \
4	-d '{
5	"voice_description": "A sassy little squeaky mouse",
6	"text": "Every act of kindness, no matter how small, carries value and can make a difference, as no gesture of goodwill is ever wasted."
7	}'

1	{
2	"previews": [
3	{
4	"audio_base_64": "audio_base_64",
5	"generated_voice_id": "generated_voice_id",
6	"media_type": "media_type",
7	"duration_secs": 1.1
8	}
9	],
10	"text": "text"
11	}