Screenshots
Watch trailer on Steam ↗Penko Vox: Japanese
penko_soft · Published by penko_soft
2 user reviews — 50% positive (2 reviews) · 8 achievements
Last updated 28 Sept 2026
A local-first, offline-capable AI Japanese language immersion engine. Step into interactive social roleplays with a private tutor and master natural usage across all JLPT levels. No cloud tracking, no subscriptions, just your own private language sandbox powered entirely by your hardware.
£22.49
Lowest price we've ever recorded
View on SteamPrices can lag the live Steam store — always confirm before buying.
Price history
Indie, RPG, Simulation, Early Access, Casual · 2026 · More £15 - £30 games
About this game
The Anki Grind is Over. Welcome to Conversational Context.
Unlike standard language apps that function as digitized textbooks, Penko Vox: Japanese is a private, local-first immersion engine designed to bridge the gap between memorizing vocabulary and using it organically in real-world environments.
By merging a professional teaching methodology with a high-performance local LLM stack, Penko Vox acts as a private conversational "Sandbox", a safe space to make mistakes, test structural syntax, and build fluency without the social anxiety or recurring cost of a live human tutor.
The Vox Core: High-Fidelity Local Intelligence
Everything runs 100% offline on your own machine, driven by a proprietary 4-step local processing architecture:
Linguistic Perception: Our integrated speech-to-text layer captures your voice input instantly, while a deep morphological analyzer atomizes your sentences into particles, stems, and conjugations for real-time structural processing.
Cognitive Processing: An offline, highly optimized local LLM acts as your native tutor. Using adaptive narrative logic, the engine advances the scenario, injects world data, and prompts your response with high-level contextual awareness.
Educational Guardrails: The engine integrates native corrective formatting, modeling correct grammar and lexical patterns back to you inside the organic flow of dialogue rather than stopping to flag red execution errors or breaking the immersion loop.
Neural Synthesis: Responses are rendered with high-fidelity local neural synthesis, allowing you to hear the precise accentuation, native pacing, and pitch mapping of natural speech profiles.
Features for Power Users & Privacy Advocates
Total Data Sovereignty
Your voice recordings, database lookups, and conversational histories never touch an external cloud or telemetry server. Zero data leaves your machine, ensuring absolute privacy.
Ownership, Not a Service
Enjoy a self-contained immersion experience with zero server dependencies. Because the neural core resides entirely on your own hardware, you face no token limits, no artificial usage tiers, and zero monthly subscription costs. One purchase provides infinite practice, your tutor is always available, completely offline.
Interactive Stroke-Order Canvas
Master the fundamentals of the Japanese writing system with an integrated, high-fidelity practice environment. Use the interactive canvas to perfect your Hiragana and Katakana stroke order with real-time visual feedback and guided animations, ensuring your literacy keeps pace with your speaking fluency.
Mastery by Output Tracking
Ditch the static flashcards. Your progress is dynamically mapped via Natural Usage metrics. When you successfully use a vocabulary word or particle sequence correctly inside an organic conversation, your baseline Mastery percentage increases automatically.
Hardware & Architecture Notice
This software runs a state-of-the-art Generative LLM model completely on consumer hardware. Performance is fully dependent on your local CPU/GPU capability. AVX2 instruction support is strictly mandatory for the local inference binaries to execute.
System Requirements
Will my PC run this? →Minimum
- Requires a 64-bit processor and operating system
- OS: Windows 10 (64-bit)
- Processor: Quad-core CPU with AVX2 support (Intel Core i5-8400 / AMD Ryzen 3 3100)
- Memory: 16 GB RAM
- Graphics: Intel UHD Graphics 630 / AMD Radeon Vega 8 (DirectX 11 / 12 compatible)
- DirectX: Version 11
- Storage: 15 GB available space
- Sound Card: Windows Compatible Sound Card
- Additional Notes: 16 GB of system RAM and AVX2 CPU instruction support are required for smooth on-device AI neural inference. Solid State Drive (SSD) is strongly recommended for fast initial model warm-up.
Recommended
- Requires a 64-bit processor and operating system
- OS: Windows 11 (64-bit)
- Processor: 6-Core / 12-Thread CPU or higher (Intel Core i5-12400 / AMD Ryzen 5 5600X)
- Memory: 32 GB RAM
- Graphics: NVIDIA GeForce RTX 3050 / RTX 3060 (4GB+ VRAM) or AMD Radeon RX 6600
- DirectX: Version 12
- Storage: 20 GB available space
- Sound Card: Windows Compatible Sound Card
- Additional Notes: An SSD and dedicated GPU provide the fastest real-time response times (sub-2 second token streaming) during voice calls and dialogue practice.
Supported Languages
*languages with full audio support
Latest news
Patch NotesOfficial
Update v2.0.0 - Offline Voice, Audio Synthesis & Engine Overhaul
- Real-Time Voice Input (Speech-to-Text): Added offline microphone voice input directly into conversational roleplay scenarios with improved stt, allowing players to speak Japanese out loud. - Offline Neural Voice Synthesis: Overhauled the Japanese Text-to-Speech engine, generating natural Japanese spoken audio directly on CPU with less latency while remaining offline and without external API calls. - Upgraded Local AI Dialogue Engine: Overhauled roleplay scenarios with local on-device LLM inference and a dynamic AI Director that guides scenario progression and adapts to your chosen JLPT level. - Interface & Window Clean-up: Removed desktop application menu bars across platforms for an immersive, borderless gaming presentation. - Steam Deck Runtime Optimization: Enhanced offline container and library paths for smooth, reliable execution in Steam Linux Runtime on Steam Deck. - Additional Note: For audio input on Steam Deck be sure to increase mic volume to get the best quality.Read full article on Community Announcements (Penko Soft)Patch NotesOfficial
Update v1.2.0 - Community Features and Enhancements
- Furigana Immersion Toggle (Community Request): Added an instant toggle in the chat header and Settings to disable Furigana above Kanji text, allowing advanced learners to practice reading raw Japanese while retaining 1-click morphological dictionary definitions. - Romaji Display Toggle: Added an instant toggle to show or hide Romanized phonetic guides similar to Furigana Toggle. - Interactive Stroke Order Calligraphy Guide (筆順) (Community Request): Added a dedicated button and interactive step scrubber to the 3D Kana & Kanji Practice Canvas. You can now watch characters drawn stroke-by-stroke in real-time or scrub through individual strokes. - Pixel Companion Visuals: Integrated retro animated pixel art backdrops, contextual scenario sprites, and dynamic visual state updates across all 28 conversational scenarios for more immersion. - Pocket Translator Upgrades: Added ruby furigana readings to translation results, and updated the action to non-destructively append to your draft. - Multi-Language Localization: Added localized UI text across all 8 supported languages for all new buttons and tools. - Stability & Performance: Optimized offline AI save pipeline and improved Linux / Steam Deck container launch stability.Read full article on Community Announcements (Penko Soft)Patch NotesOfficial
v1.0.4 Update – Penko Sensei in Chat & Audio Speedups
-Added Penko Sensei directly to the immediate chat interface, allowing players to ask Japanese grammar questions, check sentences, and get explanations without leaving the conversation. -Reallocated and balanced CPU threads to significantly speed up neural voice synthesis and dialogue generation. -Bound character tracking directly to audio playback for accurate spoken karaoke sync. -Switched audio playback to in-memory buffers for faster sound output. -Fixed on-demand Translate, Breakdown, and Grammar explanation buttons. -Updated Windows and Linux builds.Read full article on Community Announcements (Penko Soft)Patch NotesOfficial
Hotfix: Resolved Windows Download / Update Issue & Audio Fix
- Fixed an issue causing download / disk write errors on Windows during updates (resolved depot packaging and binary mapping). - Restored offline Text-to-Speech audio playback on Windows. - General packaging and stability improvements for both Windows and Linux/Steam Deck.Read full article on Community Announcements (Penko Soft)Patch NotesOfficial
Temporary Rollback to Stable Build (Build 24740666)
We have temporarily rolled back to previous stable build 24740666 while we investigate an isolated installation / disk write error reported on some Windows environments during recent updates. - Restored stable baseline for all players across Windows and Steam Deck/Linux. - We are actively diagnosing the packaging issue and will deploy an updated, verified patch shortly. Thank you for your patienceRead full article on Community Announcements (Penko Soft)
