
PhonemeX Pro Edition – Unlimited Cross Platform TTS with Phoneme Access
Carruto
$69.99
(no ratings)
Jump AssetStore
Real-time TTS with Full Phoneme Data - Unlimited Generation for All Supported Platforms✅ Works in HDRP inside the Editor, but Web builds with HDRP are not supported by Unity. Use URP or Built-in for Web. In Built-in RP, if UI input issues occur in the sample scene, select the EventSystem and click the “Fix” button in the Inspector to resolve them automatically.PhonemeX Pro Edition is a lightweight, fully offline Text-to-Speech solution built for Unity mobile and web builds. Designed for speech synthesis, character animation, lip-sync, and more – it gives you real-time audio generation and complete access to phoneme data at runtime.Documentation | Support✅ Key Features:Offline TTS – No internet or server requiredUnity Android, iOS and Web Builds CompatiblePhoneme stream output (perfect for lip sync / animation)Supports multiple voicesLightweight and fast for mobile + browserPerfect for:Games and Visual NovelsEducational platformsInteractive web toolsDigital humans and AI agentsCreated by Carruto – empowering creators with AI and audio tools.🎤 Unlimited TTS Generation – Works seamlessly in builds.🌐 Mobile and Web Build Compatibility – Optimized for mobile and browser-based games, apps, and simulations.🧠 Phoneme Access in Real-Time – Extracts and streams phoneme data alongside audio for perfect lipsync and animation syncing.⚡ Lightweight & Fast – Small runtime footprint, ideal for mobile and browser use cases.🔁 Multi-Voice Support – Easily swap between voice models (Piper format).🧩 Modular Integration – Drop-in setup with clear structure and no third-party dependencies.📦 ONNX Runtime Compatible – Uses Unity Sentis for local model inference (no server roundtrips).🎯 Cross-Platform Support – Tested on Android, iOS, Web builds, Windows, MacOS, and Linux Editors.🧪 Demo Scene Included – Ready-to-test sample with phoneme-driven animation logic.📚 Full Documentation – Setup instructions, voice model tips, and usage examples included.This package integrates pre-trained AI models to provide fully offline text-to-speech functionality. Specifically, it uses a Piper TTS voice model (in ONNX format) for local speech synthesis.