Automatic Speech Recognition

POST 
/api/v5/audio/transcriptions

Request

Header Parameters

Authorization stringrequired

User Personal Token

multipart/form-data

Body

filebinaryrequired

Audio File (supports mp3, wav, m4a, flac, webm)

modelstringrequired

Model Name, default is openai/whisper-large-v3

temperaturestring

Sample Temperature (0.0-1.0), default is 0.6

Responses

200

Response Headers

application/json

Schema

Schema

textText (string)required

Example (auto)

{
  "text": "string"
}

Example

{
  "text": "Good morning, the weather is very good today, sunny and bright. I plan to take a walk in the park, then have a cup of coffee, and start my work for the day."
}