You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: quickstart/index.html
+42-9Lines changed: 42 additions & 9 deletions
Original file line number
Diff line number
Diff line change
@@ -821,17 +821,50 @@ <h3 id="what-are-these-tools">💡 What are these tools?</h3>
821
821
<hr/>
822
822
<h2id="base-setup">⚙️ Base Setup</h2>
823
823
<ol>
824
-
<li>Go to the <ahref="https://github.com/HardCodeDev777/UnityNeuroSpeech">UnityNeuroSpeech GitHub repository</a> and download the latest Release.</li>
825
-
<li>Extract the <code>.zip</code>. You'll see:</li>
826
-
<li>a <code>.unitypackage</code></li>
827
-
<li>a <code>Server/</code> folder</li>
824
+
<li>Go to the <ahref="https://github.com/HardCodeDev777/UnityNeuroSpeech">UnityNeuroSpeech GitHub repository</a> and download the following <strong>three <code>.rar</code> files</strong> from the latest Release:</li>
825
+
<li><code>UnityNeuroSpeech.X.X.X.rar</code> – main framework files </li>
826
+
<li><code>default.venv.rar</code> – Python environment for the TTS server </li>
⚠️ <strong>Do not import the Server folder or <code>.bat</code> file into Unity. Keep them outside the project directory.</strong></li>
830
-
<li>Place your voice <code>.wav</code> files into <code>Server/Voices</code>.<br/>
831
-
Each file must follow the naming pattern: <code>en_voice.wav</code>, <code>ru_voice.wav</code>, etc.</li>
832
-
<li>Import the <code>.unitypackage</code> into Unity.</li>
833
-
<li>In the <code>UnityNeuroSpeech</code> folder, find the empty <code>Whisper</code> folder and drop your <code>.bin</code> Whisper model file into it.</li>
839
+
⚠️ <strong>Do not import the <code>Server</code> folder or <code>.bat</code> file into Unity. Keep them outside the project directory.</strong></li>
840
+
</ul>
841
+
</li>
842
+
<li>
843
+
<p>Place your <code>.wav</code> voice files into <code>Server/Voices</code>.<br/>
844
+
Each file must follow the naming pattern: <code>en_voice.wav</code>, <code>ru_voice.wav</code>, etc.</p>
845
+
</li>
846
+
<li>
847
+
<p>Move the extracted <code>.venv</code> folder (from <code>default.venv.rar</code>) into the <code>Server/</code> folder.</p>
848
+
</li>
849
+
<li>
850
+
<p>Move the extracted <code>TTSModel/</code> folder (from <code>TTSModel.rar</code>) into the <code>Server/</code> folder as well.</p>
851
+
</li>
852
+
<li>
853
+
<p>Import the <code>.unitypackage</code> into your Unity project.</p>
854
+
</li>
855
+
<li>
856
+
<p>In the <code>UnityNeuroSpeech</code> folder, you’ll see an empty <code>Whisper/</code> folder. Drop your Whisper <code>.bin</code> model file into it.</p>
857
+
</li>
834
858
</ol>
859
+
<blockquote>
860
+
<p>Some folders (like <code>Whisper/</code>) may contain <code>.txt</code> placeholder files.<br/>
861
+
These are only used to ensure Unity exports the folder. You can safely delete them after setup.</p>
862
+
</blockquote>
863
+
<hr/>
864
+
<blockquote>
865
+
<p>You can also manually install your own Python environment and download the XTTS model separately.<br/>
866
+
But if you want everything to "just work" <strong>without fighting with pip, PATH, or broken dependencies</strong> — use the provided <code>.venv</code> and <code>TTSModel</code>.</p>
867
+
</blockquote>
835
868
<hr/>
836
869
<p>✅ <strong>Done! You’re ready to build your first talking AI agent.</strong></p>
0 commit comments