Generate a text-to-speech voice message and send it directly inside a WeChat or QQ chat.
Preview and manage a library of local voice packs for messaging.
Use a cloned or preset AI voice instead of typing text into a chat.
Browse and download voices from an online catalog for use in WeChat or QQ.
| tianxing226/wtonec | galaxy-dawn/academic-homepage-templates | ruanyf/google-calendar-lite | |
|---|---|---|---|
| Stars | 45 | 46 | 43 |
| Language | CSS | CSS | CSS |
| Last pushed | — | 2026-02-19 | 2013-10-25 |
| Maintenance | — | Maintained | Dormant |
| Setup difficulty | hard | easy | moderate |
| Complexity | 4/5 | 1/5 | 2/5 |
| Audience | developer | researcher | general |
Figures from each repo's GitHub metadata at analysis time.
Requires a rooted or LSPosed-capable Android device, plus a separate Tiax API key for cloned or premium voice features.
Wtonec is an Android module that adds a voice and text to speech panel to two popular Chinese messaging apps, WeChat and QQ. It is built for the LSPosed and Xposed frameworks, which are systems that let a single installed module hook into and add features to other apps on a rooted or specially configured Android phone. One APK covers both WeChat and QQ at once, adding a new entry point inside each app's chat screen. Inside a chat, the module opens a panel where you can pick a voice, either a preset voice, a cloned voice, or the phone's own built in text to speech engine, powered by a service called Fish Audio. You type text, preview how it sounds, generate the audio, and either save it or send it straight into the chat as a voice message. It also lets you manage local voice packs: importing, searching, renaming, exporting, and deleting audio files, plus browsing and downloading from an online voice catalog. Behind the scenes it decodes whatever audio format comes back and converts it into the format WeChat and QQ expect for their normal voice message system, rather than just renaming a file. Setting it up means installing the APK, enabling it inside LSPosed, and choosing which app or apps it should apply to, then fully restarting those apps. The premium voice features, cloned voices, and the higher quality option require a personal API key from a separate service called Tiax, which you register for and paste into the module's settings. Voices generated from the phone's built in system engine or from local files do not need this key. The project's public repository includes documentation, screenshots, a small number of standalone Kotlin samples, and release builds. The core hooking logic that reaches into WeChat and QQ, along with the audio encoding and bridging code between the two apps, is kept in a separate private codebase and is not part of what is shared publicly. The README asks users to redact API keys, account details, and chat identifiers before sharing any feedback or logs.
An Android LSPosed/Xposed module that adds a text-to-speech and voice-pack panel inside WeChat and QQ chats, letting you generate and send AI voice messages.
Mainly CSS. The stack also includes Kotlin, Android, LSPosed.
The README does not state a license.
Setup difficulty is rated hard, with roughly 1h+ to a first successful run.
Mainly developer.
This repo across BitVibe Labs
Don't trust strangers blindly. Verify against the repo.