Skip to content

Custom tts api

Will send application/www-urlencode data to the specified API address via POST request:

text: 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: Name of the voice actor/string

rate: Speed adjustment value, 0 or '+number%' '-number%', representing the percentage of speed increase or decrease based on the normal speed/string

ostype: win32 or mac or linux operating system type/string

extra: Extra parameters/string

Expected JSON formatted data returned from the interface:

{

code: 0=Success in synthesis, a number >0 represents failure

msg: ok=Success in synthesis, otherwise the reason for failure

data: In case of successful synthesis, returns the complete URL of the mp3 file for download within the software. Empty in case of failure

}


OpenVoice-v2 third-party implementation of custom api

https://github.com/kungful/openvoice-api