Skip to main content
POST
/
audio
/
transcriptions
Speech-to-Text API
curl --request POST \
  --url https://geekai.dev/api/v1/audio/transcriptions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: multipart/form-data' \
  --form model=whisper-1 \
  --form file='@example-file' \
  --form 'prompt=<string>' \
  --form 'language=<string>' \
  --form response_format=text \
  --form temperature=0 \
  --form retries=0
"<string>"
Note: For speech model name settings, refer to the System Supported Transcription Speech Model List. The request/response parameter structure is fully compatible with OpenAI. When switching models, you only need to modify the corresponding model name. If the model request/response parameters are inconsistent with OpenAI, GeekAI will automatically convert and align them at the backend.
The response data format is fully compatible with the OpenAI speech transcription text interface.

​
cURL Request Example

curl --location 'https://geekai.dev/api/v1/audio/transcriptions' \
    --header 'Authorization: {YOUR_GEEKAI_API_KEY}' \
    --form 'file=@"/C:/User/GeekAI/Downloads/2cd359fe642c33deaa943f7306d73f30.mp3"' \
    --form 'model="whisper-1"' \
    --form 'response_format="text"'

Authorizations

​
Authorization
string
header
required

token

Body

multipart/form-data
​
model
string
default:whisper-1
required

transcription model

Example:

"whisper-1"

​
file
file
required

audio file

​
prompt
string

transcription prompt

​
language
string

language code

​
response_format
enum<string>
default:text

response format

Available options:
text,
srt,
vtt,
json
Example:

"text"

​
temperature
number
default:0

sampling temperature

Example:

0

​
retries
integer
default:0

auto retry times, default 0, means no retry

Example:

0

Response

successful response

text format transcription result