Custom TTS API Requirements
A POST request will be sent to the provided API address with application/www-urlencoded data:
text: The text/string to be synthesized
language: Language code of the text (zh-cn, zh-tw, en, ja, ko, ru, de, fr, tr, th, vi, ar, hi, hu, es, pt, it)/string
voice: Voice role name/string
rate: Speed adjustment value, either 0 or '+number%' or '-number%', representing the percentage increase or decrease from the normal speed/string
ostype: Operating system type, either win32, mac, or linux/string
extra: Additional parameters/string
Expect a JSON-formatted response from the interface:
{ code: 0 = synthesis successful, >0 indicates failure msg: "ok" = synthesis successful, otherwise the reason for failure data: When synthesis is successful, returns the full URL address of the MP3 file for downloading within the software. Empty when failed }
