Open-source voice AI family from Microsoft, with long-form speech recognition (ASR), multi-speaker text-to-speech (TTS), and real-time streaming TTS models.
jing332/tts-server-android
An Android system TTS app that lets phones read text aloud using custom HTTP speech services or imported local TTS engines.
- Stars
- 4,528
- Forks
- 433
- Open issues
- 91
- Last commit
- 29 days ago
What is it?
TTS Server is an Android text-to-speech app that registers as a system TTS engine, so other apps such as readers can use its voices. It ships with a built-in Microsoft demo interface and lets users define custom HTTP requests to connect other speech services.
Beyond online voices, the app can import other local TTS engines. It distinguishes narration from dialogue by Chinese double quotation marks so the two can be read with different voices. Other features include automatic retries, fallback configurations, and text replacement rules.
The project is written in Kotlin with Jetpack Compose and includes a Go-based component in its topics. Build instructions cover Android Studio and GitHub Actions with signing key setup.
Key features
- 01Acts as a system-wide Android TTS engine for other apps.
- 02Includes a built-in Microsoft demo speech interface.
- 03Supports custom HTTP requests to connect other speech services.
- 04Can import other local TTS engines.
- 05Separates narration and dialogue by Chinese double quotation marks.
- 06Offers automatic retries, fallback configurations, and text replacement.
Use cases
- Reading web novels or e-books aloud with custom voices on Android.
- Connecting a self-hosted or third-party speech API to phone-wide TTS.
- Giving character dialogue a different voice from narration.
Quick start
- 1
Download the stable APK from the Releases page
- 2
Install the APK on your Android phone and enable it as the system TTS engine
Things to know
- Android only; it is an Android system TTS app and does not run on other platforms.
- The README is written mainly in Chinese, and building from source requires setting up your own signing key.
In collections
Topics
FAQ
- What is tts-server-android?
- An Android system TTS app that lets phones read text aloud using custom HTTP speech services or imported local TTS engines. TTS Server is an Android text-to-speech app that registers as a system TTS engine, so other apps such as readers can use its voices. It ships with a built-in Microsoft demo interface and lets users define custom HTTP requests to connect other speech services.
- Is tts-server-android free to use? What license does it have?
- tts-server-android has no declared license. Its code is public, but without a license you have no explicit permission to reuse it; ask the author before relying on it.
- Is tts-server-android still maintained?
- Actively maintained. The last commit to tts-server-android was on Sep 24, 2026.
- What can I use tts-server-android for?
- Reading web novels or e-books aloud with custom voices on Android. Connecting a self-hosted or third-party speech API to phone-wide TTS. Giving character dialogue a different voice from narration.
- How do I install tts-server-android?
- Download the stable APK from the Releases page Install the APK on your Android phone and enable it as the system TTS engine
- Where can I get tts-server-android?
- The source code and installation instructions are on GitHub: https://github.com/jing332/tts-server-android
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
Open-source text-to-speech system with voice cloning, natural-language emotion control and multi-speaker generation, built on LLM-style models.
A zero-shot text-to-speech system that clones a voice from one reference audio clip, with emotion, speed and pronunciation control.
Python inference library for Kokoro-82M, an open-weight text-to-speech model with 82 million parameters.
A fast, local neural text-to-speech engine that uses espeak-ng for phonemization, installable via pip.
Python package for offline text-to-speech using the Kokoro model running on ONNX Runtime, with CPU and GPU support.