All Games > Casual Games > 知秋~英语日语单词背诵学习陪伴桌宠~ > Downloadable Content > 知秋桌宠 - 高质量语音推理基座
Community Hub
知秋桌宠 - 高质量语音推理基座

This content requires the base game 知秋~英语日语单词背诵学习陪伴桌宠~ on Steam in order to play.

Release Date:
Nov 1, 2026
Developer:
Publisher:
无水硫酸铜
Tags
Popular user-defined tags for this product:
+

Sign in to add this item to your wishlist, follow it, or mark it as ignored

Features
Languages:
Interface Full Audio Subtitles
English ✔
Simplified Chinese ✔ ✔ ✔
Japanese ✔
English language not supported

This product does not have support for your local language. Please review the supported language list below before purchasing

Downloadable Content

This content requires the base game 知秋~英语日语单词背诵学习陪伴桌宠~ on Steam in order to play.

 

About This Content

A prerequisite for Qwen3-TTS speech

This free DLC supplies the Qwen3-TTS inference components used by Zhiqiu. It contains no character voice model and has no standalone launcher. Installing this component alone does not enable speech generation.

Install the complete set

  • The Zhiqiu base game.
  • The GPT-SoVITS voice-runtime DLC: install this prerequisite first because it supplies the shared Python environment.
  • This Qwen3-TTS voice-runtime DLC.
  • The separately installed Zhiqiu Qwen3-TTS voice-model DLC. The model is not included in this runtime.

Installation and use

  • In the Steam library, open the base game’s Properties > DLC, enable both runtimes and the Qwen3-TTS voice model, and wait for every download to finish.
  • Launch the base game. Open Settings > Resources & MODs and check that both runtimes and the model are recognized. Install any missing component shown there.
  • Select the Qwen3-TTS voice model and enable real-time text-to-speech (TTS) in Settings > Voice. Wait for initialization and the voice service to become ready.
  • Edit a character’s petting line to hear newly synthesized speech. Turn off the option to prioritize attached pre-recorded audio when testing live synthesis.

Generative AI and performance

With its prerequisites and matching voice model installed, this DLC runs local generative AI to synthesize new speech audio from text. It does not generate chat-response text. Qwen3-TTS requires a higher-performance computer; initial loading and synthesis take time and depend on your CPU, GPU and memory. The base game’s fixed pre-recorded voices do not require this DLC.

AI Generated Content Disclosure

The developers describe how their game uses AI Generated Content like this:

This DLC provides Qwen3-TTS inference components, not a character voice model. With the base game, the GPT-SoVITS runtime supplying the shared Python environment, and the separately installed Qwen3-TTS voice model, it uses local generative AI to synthesize new speech audio from text. This DLC alone cannot speak. It does not generate chat text, images, music or code.

System Requirements

    Minimum:
    • Requires a 64-bit processor and operating system
    • OS: Windows 10 64-bit
    • Processor: 64-bit dual-core processor
    • Memory: 4 GB RAM
    • Graphics: DirectX 11-compatible integrated or discrete graphics
    • DirectX: Version 11
    • Storage: 2 GB available space
    • Sound Card: Windows-compatible audio device
    • Additional Notes: These requirements cover the core vocabulary-study and desktop-companion features. Optional local TTS runtime and voice-model DLCs require additional storage and computing resources.
    Recommended:
    • Requires a 64-bit processor and operating system
    • OS: Windows 11 64-bit
    • Processor: Modern 6-core x64 processor
    • Memory: 16 GB RAM
    • Graphics: NVIDIA GPU with 6 GB VRAM and current drivers for accelerated local GPT-SoVITS TTS; Qwen3-TTS requirements depend on the selected model.
    • DirectX: Version 11
    • Storage: 16 GB available space
    • Sound Card: Windows-compatible audio device
    • Additional Notes: Recommended hardware is intended for optional local TTS. Install matching runtime and voice-model resources and enable real-time TTS in Settings > Voice. CPU inference can be slower; Qwen3-TTS resource requirements vary by model. LLM chat and cloud speech require separately installed and configured Workshop extensions.