Skip to main content
POST
/
v1
/
openai
/
audio
/
transcriptions
from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

with open("sample.mp3", "rb") as audio_file:
    response = client.audio.transcriptions.create(
        model="<transcription-model-id>",
        file=audio_file,
    )

print(response.text)

{
  "detail": [
    {
      "loc": [
        "<string>"
      ],
      "msg": "<string>",
      "type": "<string>",
      "input": "<unknown>",
      "ctx": {}
    }
  ]
}
Authentication is optional. See Rate Limits for per-tier quotas. For available transcription models, see Models. 
from openai import OpenAI

client = OpenAI(
    base_url="https://gateway.vlm.run/v1/openai",
    api_key="<VLMRUN_API_KEY>",
)

with open("sample.mp3", "rb") as audio_file:
    response = client.audio.transcriptions.create(
        model="<transcription-model-id>",
        file=audio_file,
    )

print(response.text)

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

multipart/form-data
​
model
string
required
​
file
string | null
​
url
string | null
​
language
string | null
​
prompt
string | null
​
response_format
string
default:json
​
temperature
number
default:0
​
timestamp_granularities[]
string[] | null

Response

Successful Response