Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Xiaoya Children's Voice Companion releases r4 with GPU speech synthesis

AI summary

The author released r4 of the Windows desktop app Xiaoya Children's Voice Companion, adding DirectML GPU speech synthesis, wake-word interaction, and an interface for self-hosted OpenAI-compatible language model services. The app can use DeepSeek's official service or a compatible self-hosted backend, while speech recognition and synthesis run locally; the app does not download or host the self-hosted model. In the author's test on an RTX 4060 Laptop, warmed-up speech synthesis averaged about 0.32 seconds on the GPU versus 5.16 seconds on the CPU, covering only the synthesis stage.

In-depth insight

The release provides a complete C# reference implementation for wake-word interaction, local speech recognition, streaming model responses, speech synthesis, playback, and DirectML adaptation, although its performance figures come from the author alone.

“为什么下雨以后,天空会出现彩虹?”

“给我讲一个关于勇气和友谊的小故事吧。”

“我们一起练习用英语打招呼,好不好?”

小朋友的脑袋里,总有许多有趣的问题。

最近,我把这些日常场景做进了一个 Windows 桌面软件,给它起名叫  “小芽 · 儿童语音伙伴” 。打开语音模式,喊一声“小芽小芽”,听到“我在,请说”,就可以直接提问。

它能显示回答,也能把回答读出来。家长可以和孩子一起听故事、聊科普、练英语,开发者也可以打开完整源码,研究一个语音助手从收音到开口的实现过程。

#Xiaoya Children's Voice Companion#Kokoro#SenseVoice#DeepSeek#DirectML#RTX 4060 Laptop#OpenAI Chat Completions

Original · 8 min readRead the original
Group chat

No comments yet. Start the conversation.