tts-server-proxy

# πŸ”Š tts-server-proxy **A real Android system TTS engine that speaks with your own self-hosted Qwen3-TTS voices.** Every app on your phone β€” readers, assistants, accessibility tools β€” talks with the voices running on **your GPU, on your LAN**. No cloud, no subscriptions, no per-character fees. ![Platform](https://img.shields.io/badge/platform-Android%208.0%2B-3DDC84?logo=android&logoColor=white) ![API](https://img.shields.io/badge/API-26–35-1565C0) ![Release](https://img.shields.io/badge/release-v0.6.1-1E88E5) ![License](https://img.shields.io/badge/license-MIT-green) ![Cloud](https://img.shields.io/badge/cloud-none-success) [Installation](#-installation) Β· [How it works](#-how-it-works) Β· [Server setup](#-server-side) Β· [Troubleshooting](#-troubleshooting)

πŸ€” Why

Android’s built-in TTS voices are robotic, locked to Google’s cloud, or missing entirely for your language. If you run a Qwen3-TTS server (or any OpenAI-compatible speech endpoint) you already have great, clonable voices β€” but Android apps can’t use them.

tts-server-proxy bridges that gap: it installs as a first-class TextToSpeechService, so it appears in Settings β†’ System β†’ Languages & input β†’ Text-to-speech output like any commercial engine. Whatever the system asks it to speak, it synthesizes on your server and streams back to the app that requested it.

Use cases:

βš™οΈ How it works

β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  TextToSpeech API   β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”  OpenAI-compatible   β”Œβ”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”
β”‚  Any Android β”‚ ──── bind ────────► β”‚  tts-server-proxy  β”‚ ──── POST ─────────► β”‚  Your GPU server    β”‚
β”‚  app         β”‚ ◄── PCM 16-bit ──── β”‚  (system engine)   β”‚ ◄── WAV/MP3 ──────── β”‚  Qwen3-TTS          β”‚
β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜                     β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜  /v1/audio/speech    β””β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”€β”˜

The app speaks OpenAI’s audio-speech dialect:

POST {endpoint}/v1/audio/speech
{
  "model":  "qwen3-tts-1.7b_G0",
  "voice":  "clone:VoceItalianaAdulta",
  "input":  "Text to speak",
  "response_format": "wav"
}

πŸ“± Installation

Option A β€” prebuilt APK

  1. Grab tts-server-proxy-v0.6.1.apk from the latest release (or from apk/ in this repository).
  2. Install it (allow β€œinstall unknown apps” if asked).
  3. Open the app: endpoint, model and voice come pre-filled with a sensible default β€” edit them, paste your API key, tap πŸ’Ύ Save configuration.
  4. Select the engine: Settings β†’ System β†’ Languages & input β†’ Text-to-speech output β†’ tts-server-proxy
  5. Hit πŸ”Š Test synthesis inside the app and listen. 🎧

The engine also works before you ever open the app: if no configuration is found, built-in defaults are used, so a fresh install (or a reboot) keeps talking.

Option B β€” build from source

git clone https://github.com/manu69x/tts-server-proxy.git
cd tts-server-proxy
export ANDROID_HOME=/path/to/android-sdk
gradle :app:assembleRelease          # or :app:assembleDebug for a debug build

Requirements: JDK 17, Android SDK 35, Gradle 8.10+ (AGP 8.6). Release builds expect app/keystore.properties + app/release.keystore.jks (not committed β€” see below); debug builds work out of the box.

πŸ–₯️ Server-side

Any endpoint that accepts OpenAI-style /v1/audio/speech and returns WAV/MP3 audio will work. The stack this app was built and tested against:

Android phone
  β†’ Phoenix        (wake-on-LAN proxy, OpenAI-compatible front door)
  β†’ llama-swap     (model router / pool, GPU instances)
  β†’ Qwen3-TTS      (FastAPI serving Qwen3-TTS 0.6B/1.7B models on one or more GPUs)

You don’t need all of that β€” a single FastAPI service exposing /v1/audio/speech is enough. Quick sanity check from any machine on the LAN:

curl -X POST http://YOUR_SERVER:PORT/v1/audio/speech \
  -H "Content-Type: application/json" -H "Authorization: Bearer sk-..." \
  -d '{"model":"qwen3-tts-1.7b_G0","voice":"clone:MyVoice","input":"hello","response_format":"wav"}'

No Linux box? Ready-made compatible servers

Any OpenAI-compatible /v1/audio/speech server works β€” including native Windows options that need nothing but a double-click:

Server Difficulty GUI Cloning Italian Docs
Chatterbox-TTS-Server β˜…β˜†β˜† Easy (Windows portable, zero install) βœ… βœ… βœ… guide
Kokoro-FastAPI β˜…β˜…β˜† Medium (Windows/uv or Docker) βœ… ❌ preset voices βœ… guide
AllTalk TTS V2 β˜…β˜…β˜† Medium (Windows setup script) βœ… βœ… XTTS βœ… guide
Qwen3-TTS on Linux β˜…β˜…β˜… Advanced ❌ βœ… zero-shot βœ… guide

Full comparison + per-server install instructions and the exact app config: docs/servers/README.md.

πŸ–ΌοΈ Screenshots

Configuration Synthesis test Diagnostics
Configuration Test Diagnostics

Material 3 UI, follows system dark mode. One model in the list = one voice in Android’s voice picker.

🧰 Features

πŸš‘ Troubleshooting

Symptom Cause / fix
Engine doesn’t appear in the TTS list Reboot once after install; the engine registers itself β€” no account needed
First synthesis takes 10 s–3 min Cold start: the server wakes and loads the model. Next requests are fast (~3 s)
β€œSpeech engine problem” dialog Update to β‰₯ v0.3.2 β€” cancelled requests no longer surface errors
No audio on some servers The app auto-detects MP3 and decodes it; ensure the endpoint returns valid audio
Wrong voice used by default The engine picks the first model matching the requested language β€” order your model list accordingly
Need to see what’s happening Open Diagnostics β†’ πŸ“„ debug.log: the service logs every synthesis step there

πŸ” Privacy & security

Speech, text and API key never leave your LAN. HTTP is used in cleartext by design β€” run it on a network you trust (or wire up TLS on your front proxy). Signing keys are not in this repository: app/keystore.properties and app/release.keystore.jks are gitignored; generate your own with keytool to sign your builds.

πŸ“„ License

MIT β€” Β© 2026 Emanuele Viani


Built with 🎧 by [@manu69x](https://github.com/manu69x) β€” voices by [Qwen3-TTS](https://github.com/QwenLM/Qwen3), routing by [llama-swap](https://github.com/mostlygeek/llama-swap). Another project by the same author: [**Battery Test**](https://batterytest.altervista.org) β€” measure your laptop's real battery life with a server-verified test. Free, no registration.