cg小白兔 发表于 2023-8-22 12:24:30

【更新】Speech Recognition using Google Cloud [VRARMobileDesktop] Pro 4.3.1

本帖最后由 cg小白兔 于 2023-8-22 13:27 编辑



















Speech Recognition using Google Cloud a true tool for Unity which provides functionality for:
• The recording of voice and the recognition of it
• Setup of Speech Context
• Support of 120 languages and variants
• Fast Speech Recognition
• Offers selection of pre-built models, tailored for your use case
• Automatically transcribes proper nouns and context-specific formatting
• Full included Google Cloud Speech REST API*
• Runtime Voice Detection feature

Based on Google Cloud Speech Recognition
Warning:
• Be sure to read the terms of service of Google Cloud Speech Recognition
• The plugin does not cover the cost of Google Cloud Service
• The plugin does not include Google Cloud Storage API - it means Long Recognize can record only 60 seconds of an AudioClip
In Pro version - Full source code Included!
Most necessary for communications in VR\AR games and applications!

Note:
• Works with il2cpp.
• Tested on:
---Android
---IOS
---Windows
---Mac
---Linux
• Works with Unity Cloud Build.
• Doesn't support streaming speech recognition*
• Works in WebGL with integrated Microphone WebGL Library
• Streaming Speech Recognition


使用谷歌云的语音识别是 Unity 的真正工具,可提供以下功能:
- 语音录制和识别
- 设置语音上下文
- 支持 120 种语言和变体
- 快速语音识别
- 提供预建模型供选择,为您的使用情况量身定制
- 自动转录专有名词和特定语境格式
- 包含完整的谷歌云语音 REST API*
- 运行时语音检测功能

基于谷歌云语音识别
警告:
- 请务必阅读 Google 云语音识别的服务条款
- 该插件不包括谷歌云服务的费用
- 插件不包含谷歌云存储 API - 这意味着 Long Recognize 只能录制 60 秒的音频片段
在专业版中 - 包含完整源代码!
VR\AR 游戏和应用程序中最需要的通信功能!

请注意:
- 与 il2cpp 一起使用。
- 已在以下平台测试
--安卓
---操作系统
--Windows
---苹果
--Linux
- 可与 Unity 云构建一起使用。
- 不支持流式语音识别*。
- 通过集成的麦克风 WebGL 库在 WebGL 中运行
- 流式语音识别






kuanyidairen 发表于 2023-11-8 12:38:01

通过集成的麦克风 WebGL 库在 WebGL 中运行
页: [1]
查看完整版本: 【更新】Speech Recognition using Google Cloud [VRARMobileDesktop] Pro 4.3.1