基于阅读和GSVI的AI听书

用Gemini跑出来的一个简陋的东西，因为我主要是用阅读，所以其他的小说软件需要自己测试。成品如下


http://192.168.x.x:8000/v1/audio/speech,{"method":"POST","headers":{"Content-Type":"application/json"},"body":{"input":"{{speakText}}","model":"模型版本","voice":"模型名称","other_params":{"text_split_method":"切分方法","emotion":"参考情感"}}}

直接将其中的红字换成对应信息，然后在阅读的添加朗读引擎里，复制到url一栏中，在content-type里填入audio/wav，下面是我个人的配置用作示例。


http://192.168.0.100:8000/v1/audio/speech,{"method":"POST","headers":{"Content-Type":"application/json"},"body":{"input":"{{speakText}}","model":"GSVI-v2ProPlus","voice":"知更鸟","other_params":{"text_split_method":"按标点符号切","emotion":"中立"}}}