Skip to main content
POST
/
v1
/
audio
/
translations
Create translation
curl --request POST \
  --url https://api.dgrid.ai/v1/audio/translations \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form file='@example-file' \
  --form 'model=<string>' \
  --form 'prompt=<string>' \
  --form response_format=json \
  --form temperature=0
{
  "text": "<string>"
}

Authorizations

​
Authorization
string
header
required

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

Body

multipart/form-data
​
file
file
required

Source audio file.

​
model
string
required

Model ID, such as whisper-1.

​
prompt
string

Optional English prompt.

​
response_format
enum<string>
default:json
Available options:
json,
text,
srt,
verbose_json,
vtt
​
temperature
number
default:0

Sampling temperature.

Required range: 0 <= x <= 1

Response

English translation result.

​
text
string

English translation of the uploaded audio.