음성 생성 - DGrid AI Docs

curl --request POST \ --url https://api.dgrid.ai/v1/audio/speech \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "model": "tts-1", "input": "Hello from DGrid.", "voice": "alloy" } '

인증

Authorization

string

header

필수

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

본문

application/json

model

string

필수

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

예시:

"tts-1"

input

string

필수

Text to synthesize, up to 4096 characters.

voice

enum<string>

필수

Voice preset.

사용 가능한 옵션:

alloy,

echo,

fable,

onyx,

nova,

shimmer

response_format

string

기본값:mp3

Output audio format.

speed

number

기본값:1

Speaking speed.

필수 범위: 0.25 <= x <= 4

응답

Binary audio stream.

The response is of type file.