所有遊戲 > 模擬 遊戲 > Megan AI
社群中心
Megan AI
Chat with a lifelike AI companion that runs on your own PC. Type or speak to a MetaHuman avatar powered by on-device language models. Swap GGUF models, tune prompts, and watch the conversation unfold in real time—offline, no cloud required

登入以將此項目新增至您的願望清單、關注它，或標記為已忽略

功能
單人
親友同享
個人檔案功能受限 
需要同意第三方使用者授權合約（EULA）
語言:
介面 完整語音 字幕
繁體中文 不支援
英文 ✔ ✔ ✔

即將推出搶先體驗

此遊戲的開發者打算以開發中的狀態推出遊戲，以將玩家意見回饋納入開發過程。

備註：處於搶先體驗狀態的遊戲尚未開發完成，且內容可能會有所變動。如果目前的開發進度未使您產生興趣， 建議您等待本遊戲開發至下一階段時再決定是否購買。了解更多

開發者的話：

為何採用搶先體驗模式？

「Megan AI is an unusual blend of local LLM sandbox and real-time MetaHuman avatar. We need a wide variety of hardware, models, and use-cases to finish polishing stability, voice flow, and UX. Shipping in Early Access lets curious users try the tech now and steer our priorities with real-world feedback instead of guesses.」

這款遊戲的搶先體驗時間大約會持續多久？

「Our current roadmap points to 6–12 months in Early Access.
If big breakthroughs—or big surprises—occur, that window may shift. We’ll keep the community informed as we hit each milestone.」

正式版預計會與搶先體驗版有何不同？

「The 1.0 release is planned to include:

Additional MetaHuman presets and environment maps

Expanded voice library and on-device TTS options

Long-term memory & summarised chat history

One-click model hot-swap and auto-download from Hugging Face

VR interaction prototype (head-tracked eye contact, gesture control)

Stability, performance, and crash-guard improvements
Scope may evolve based on community feedback; features will roll out as they’re ready rather than all at once.」

搶先體驗版目前的開發進度如何？

「Fully playable and fully offline.

Text or voice chat with a MetaHuman powered by any GGUF model you drop in

Three Apache-2.0 7 B starter models bundled

Real-time lip-sync, prompt editor, context window display, basic crash recovery

Settings menu for CPU/GPU layers, temperature, speech mode
Known limitations: occasional avatar animation pops, no long-term memory yet, UI is programmer-art, and some models may ignore safety prompts.」

遊戲售價在搶先體驗期間前後會有所變動嗎？

「Yes. Early Access is priced to reward early adopters. We expect to increase the price gradually as major features (memory, new avatars, VR mode) are shipped.」

在開發過程中，您打算如何與社群互動？

「Steam Community Hub – fortnightly dev-logs and public bug tracker threads

Discord server for quicker feedback, model swaps, and scheduled beta branches

Opt-in experimental branch on Steam for users who want to test fixes before they hit the main build
We read every post, surface common issues in the Trello roadmap, and vote on feature priorities with the community.」
繼續閱讀
不支援繁體中文

本產品尚不支援您的目前所在地的語言。購買前請先確認語言支援清單。

加入 Megan AI Playtest 測試

可要求存取權，開發者準備好開放給更多參與者測試時將會通知您。
要求存取權
此遊戲尚未在 Steam 上發售

即將推出

感興趣嗎？
將這款遊戲加入願望清單，以便在發售時收到通知。
新增至您的願望清單
 
查看所有討論

在討論區回報錯誤並留下對於此遊戲的意見

關於此遊戲

Overview

Megan AI is a single-player sandbox that turns your PC into a fully offline AI companion.
Load any compatible GGUF language model, give it a voice and face, and chat by text or microphone while a MetaHuman lip-syncs every reply.

Key Features

  • Local language models – Four Apache-2.0 7 B models included; drop in your own GGUF files.
  • Voice input & output – Speech-to-text via Wit.ai* and crystal-clear TTS with SherpaOnnx.
  • Real-time MetaHuman – High-fidelity avatar driven by UE 5.6 with precision lip-sync.
  • Prompt sandbox – Edit system prompts, adjust temperature, context window, GPU layers.
  • No cloud, no telemetry – All conversations stay on your machine.
  • Early Access roadmap – Weekly updates: model hot-swap, Workshop personality sharing, GPU off-load optimisations.

*Voice input is optional. No audio is stored or uploaded.

Why Early Access?

We’re a tiny indie team, and your feedback will decide which models, prompts, and features we polish first. Join the community hub, post conversation screenshots, and help us shape the future of personal AI!

AI 生成內容聲明

開發者針對他們的遊戲使用 AI 生成內容方式的說明如下：

Megan AI runs a local language model on your PC to generate dialogue and text-to-speech replies in real time. No conversation data leaves your machine.

成人內容說明

開發者表示產品內容如下：

Megan AI is a free-form conversational experience.
All dialogue is generated live by an on-device language model based on your prompts. While we ship a default “no explicit content” system prompt, the AI may still produce occasional coarse language, references to mature themes, or user-requested role-play that some players find inappropriate. There is no built-in graphic violence, pornography, or hate speech, and no visual depictions of nudity or gore. You can clear the chat history or reset the AI at any time

系統需求

    最低配備:
    • 作業系統: Windows 10 64-bit
    • 處理器: Intel Core i5-8400 / AMD Ryzen 5 2600
    • 記憶體: 16 GB 記憶體
    • 顯示卡: NVIDIA GTX 1060 6 GB or equivalent
    • DirectX: 版本：11
    • 網路: 寬頻網際網路連線
    • 儲存空間: 15 GB 可用空間
    • 音效卡: DirectX-compatible
    • 備註: Uses on-device AI; lower-end CPUs/GPUs may see slower replies.
    建議配備:
    • 作業系統: Windows 10/11 64-bit
    • 處理器: Intel Core i7-10700 / AMD Ryzen 7 3700X
    • 記憶體: 32 GB 記憶體
    • 顯示卡: NVIDIA RTX 3060 12 GB or better
    • DirectX: 版本：12
    • 網路: 寬頻網際網路連線
    • 儲存空間: 20 GB 可用空間
    • 音效卡: DirectX-compatible
    • 備註: GPU off-load improves AI speed; headset mic recommended for voice chat.
此產品無任何評論

您可以撰寫評論來與社群分享您對於本產品的看法。請使用本頁面中位於購買按鈕上方的區塊來進行評論的編寫。