建立語音 - 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" } '

授權

Authorization

string

header

必填

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

主體

application/json

model

string

必填

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

範例:

"tts-1"

input

string

必填

Text to synthesize, up to 4096 characters.

voice

enum<string>

必填

Voice preset.

可用選項:

alloy,

echo,

fable,

onyx,

nova,

shimmer

response_format

string

預設值:mp3

Output audio format.

speed

number

預設值:1

Speaking speed.

必填範圍: 0.25 <= x <= 4

回應

Binary audio stream.

The response is of type file.