Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

求助:S12小爱音箱,设置了"mute_xiaoai": true但是感觉延迟很高,每次都会先回答出几个小爱自己的输出字眼然后才会询问chatGPT #457

Open
EasonFang opened this issue Mar 15, 2024 · 10 comments

Comments

@EasonFang
Copy link

No description provided.

@yihong0618
Copy link
Owner

这个做到完全 mute 很难。。。不建议。
S12 应该 mute 效果没那么好。

@EasonFang
Copy link
Author

好的好的,谢大佬!

@kidxiang
Copy link

我也是S12,S12是不是只能用小米自己的tts?我换成edge就没有声音了(后台有文字输出)

@yihong0618
Copy link
Owner

我也是S12,S12是不是只能用小米自己的tts?我换成edge就没有声音了(后台有文字输出)

你是docker 用的么?
用 openai 和 azure 试试

@kidxiang
Copy link

我也是S12,S12是不是只能用小米自己的tts?我换成edge就没有声音了(后台有文字输出)

你是docker 用的么? 用 openai 和 azure 试试

是用的docker,晚上回去试试openai 和 azure

@kidxiang
Copy link

kidxiang commented Apr 19, 2024

试了azure,还是不放音(后台有文字输出),看来S12是不支持其他tts了

@yihong0618
Copy link
Owner

s12 理论上是支持的。。。

  1. 用最新的 images 试试
  2. 用代码跑试试,不用 docker
  3. 确认下你 docker 跑是按照 readme 的,给加个 env

@kidxiang
Copy link

s12 理论上是支持的。。。

  1. 用最新的 images 试试
  2. 用代码跑试试,不用 docker
  3. 确认下你 docker 跑是按照 readme 的,给加个 env

已使用最新的image,还是不能播放azure的tts,麻烦大佬帮忙看看配置呢

config.json的配置如下

/docker/xiaogpt# vi config.json
{
"hardware": "S12",
"account": "xxxxx@xxx.com",
"password": "xxxxxxxx",
"gemini_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"mi_did": "151104824",
"use_command": false,
"mute_xiaoai": true,
"verbose": false,
"bot": "doubao",
"tts": "azure",
"tts_options": {
"speech_key": "xxxxxxxxxxxxxxxxxxxx",
"speech_region": "eastasia"
},
"prompt": "请一步一步的思考后再回答我的问题",
"keyword": ["请"],
"change_prompt_keyword": ["更改提示词"],
"start_conversation": "开始持续对话",
"end_conversation": "结束持续对话",
"stream": true,
"volc_access_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",
"volc_secret_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"
}

以下是日志的截图,用的群晖的docker启动的
image

docker的环境变量截图
image

@kidxiang
Copy link

s12 理论上是支持的。。。

  1. 用最新的 images 试试
  2. 用代码跑试试,不用 docker
  3. 确认下你 docker 跑是按照 readme 的,给加个 env

已使用最新的image,还是不能播放azure的tts,麻烦大佬帮忙看看配置呢

config.json的配置如下

/docker/xiaogpt# vi config.json { "hardware": "S12", "account": "xxxxx@xxx.com", "password": "xxxxxxxx", "gemini_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx", "mi_did": "151104824", "use_command": false, "mute_xiaoai": true, "verbose": false, "bot": "doubao", "tts": "azure", "tts_options": { "speech_key": "xxxxxxxxxxxxxxxxxxxx", "speech_region": "eastasia" }, "prompt": "请一步一步的思考后再回答我的问题", "keyword": ["请"], "change_prompt_keyword": ["更改提示词"], "start_conversation": "开始持续对话", "end_conversation": "结束持续对话", "stream": true, "volc_access_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx", "volc_secret_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx" }

以下是日志的截图,用的群晖的docker启动的 image

docker的环境变量截图 image

搞定了,加了一个环境变量XIAOGPT_HOSTNAME,就可以了
谢谢大佬的耐心回答,还是自己readme文件没看得仔细

@yihong0618
Copy link
Owner

s12 理论上是支持的。。。

  1. 用最新的 images 试试
  1. 用代码跑试试,不用 docker
  1. 确认下你 docker 跑是按照 readme 的,给加个 env

已使用最新的image,还是不能播放azure的tts,麻烦大佬帮忙看看配置呢

config.json的配置如下

/docker/xiaogpt# vi config.json

{

"hardware": "S12",

"account": "xxxxx@xxx.com",

"password": "xxxxxxxx",

"gemini_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",

"mi_did": "151104824",

"use_command": false,

"mute_xiaoai": true,

"verbose": false,

"bot": "doubao",

"tts": "azure",

"tts_options": {

"speech_key": "xxxxxxxxxxxxxxxxxxxx",

"speech_region": "eastasia"

},

"prompt": "请一步一步的思考后再回答我的问题",

"keyword": ["请"],

"change_prompt_keyword": ["更改提示词"],

"start_conversation": "开始持续对话",

"end_conversation": "结束持续对话",

"stream": true,

"volc_access_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx",

"volc_secret_key": "xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx"

}

以下是日志的截图,用的群晖的docker启动的

image

docker的环境变量截图

image

你能试下 micli play url 能不能播放东西么

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

3 participants