Skip to main content
POST
Create speech

Autorisations

Authorization
string
header
requis

Your DGrid API key. All endpoints use Authorization: Bearer <DGRID_API_KEY>.

Corps

application/json
model
string
requis

Voice model, such as tts-1 or tts-1-hd.

Exemple:

"tts-1"

input
string
requis

Text to synthesize, up to 4096 characters.

voice
enum<string>
requis

Voice preset.

Options disponibles:
alloy,
echo,
fable,
onyx,
nova,
shimmer
response_format
string
défaut:mp3

Output audio format.

speed
number
défaut:1

Speaking speed.

Plage requise: 0.25 <= x <= 4

Réponse

Binary audio stream.

The response is of type file.