AI Text to Speech

AI quickly converts text into ultra-realistic speech. Supports various voice types, including male, female, child, formal, and other voices. It also supports multiple languages, including Spanish, French, German, Portuguese, Japanese and more.

1.1 Create Task

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

Request Params

  • text * string

    Text to be Synthesized Choose between text and srt, with text having higher priority.

  • srt * array

    Subtitles to be Synthesized Choose between text and srt, with text having higher priority.

    • start * int

      Start Time In milliseconds

    • end * int

      End Time In milliseconds

    • text * string

      Your text

  • mode * int

    Mode (Voice Library)
    1: Classic Voice
    2: Extended Voice

  • language * string

    Voice Language (based on the selected mode)
    You can find the specific languages in the table below.

  • voice * string

    Voice: Default is Xiaoyun
    *Voices are matched based on the selected language. Click to view the .

  • filename * string

    Download Filename upon Task Completion Required, must start with wx-tts

  • volume int

    Volume: Range is 0-100, default is 50

  • speech_rate int

    Speech Rate: Range is -500 to 500, default is 0

  • format string

    Audio Encoding Format Default is mp3, aac is optional

Response Params

  • task_id string

    Task ID: Required for subsequent progress queries.

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.