AI Speech to Text

AI quickly converts audio and video into text with high accuracy using advanced AI models. It also supports translation into major global languages.

1.1 Create Task

POST https://techhk.aoscdn.com/api/tasks/audio/recognition

Request Params

  • url * string

    File URL: Must be a resolvable HTTP URL. If the URL lacks a file extension, specify extension, e.g., extension=mp3. Max 512 characters. Download timeout is 5 minutes (failure if not completed within 5 minutes).

  • type * int

    Mode: Enter 4

  • content_type * int

    Content Type: Enter 1

  • extension string

    File Extension: Required if the URL lacks a file extension.

  • language string

    Audio Language: Optional. Defaults to automatic detection. Supported languages are listed in the appendix.

  • speaker_recognition int

    Speaker Recognition: Detect different speakers, 0 - no (default), 1 - yes.

Response Params

  • task_id string

    Task ID: Needed for progress tracking.

Copyright © 2025 RecCloud All Rights Reserved 條款隱私Cookies策略
返回頂部

本網址使用對本網站的運營及其核心功能至關重要的 cookie,只有在您同意的情況下才會放置其他 cookie。想要了解更多詳情,請訪問我們的 隱私策略.