Skip to main content

Asynchronous - Speech to Text API​

Create inference by uploading file

POSThttps://longrun-api.dev.visai.ai/v1/job/stt/predict/files
Header
    X-API-Key string required

    Your API key

form-data body

Request Body
  • files Filerequired

    Audio raw files in a form of multi-part form data using the key name files.

    The maximum size for each file is 1 GB.

    The duration of each file should less than 300 minutes.

optional

Send with the form of multi-part form data

    files_speakers file

    Speaker file Maximum 5 files can be provided. Each file size must not exceed 20 MB.

    boosting_words string

    Enhances recognition accuracy for specific words. Maximum 10 words can be provided. e.g., สวัสดี

Responses
object
job_id string

ID of the inference job

Loading...