Merge pull request SciSharp#1009 from gunpal5/master

fix: Google realtime communication

Author: Oceania2018

src/Infrastructure/BotSharp.Core.Realtime/Services/WaveStreamChannel.cs

@@ -25,7 +25,7 @@ public async Task ConnectAsync(string conversationId)
         _waveIn = new WaveInEvent
         {
             DeviceNumber = 0, // Default recording device
-            WaveFormat = new WaveFormat(24000, 16, 1), // 24000 Hz, 16-bit PCM, Mono
+            WaveFormat = new WaveFormat(16000, 16, 1), // 24000 Hz, 16-bit PCM, Mono
             BufferMilliseconds = 100
         };
 

src/Plugins/BotSharp.Plugin.GoogleAI/Providers/Realtime/RealTimeCompletionProvider.cs

@@ -79,7 +79,7 @@ public async Task Connect(RealtimeHubConnection conn,
 
         await AttachEvents(_client);
 
-        await _client.ConnectAsync();
+        await _client.ConnectAsync(false);
     }
 
     public async Task Disconnect()
@@ -96,7 +96,7 @@ public async Task AppenAudioBuffer(string message)
     public async Task AppenAudioBuffer(ArraySegment<byte> data, int length)
     {
         var buffer = data.AsSpan(0, length).ToArray();
-        await _client.SendAudioAsync(buffer);
+        await _client.SendAudioAsync(buffer,"audio/pcm;rate=16000");
     }
 
     public async Task TriggerModelInference(string? instructions = null)
@@ -285,10 +285,14 @@ await HookEmitter.Emit<IContentGeneratingHook>(_services,
             });
         }
 
+        // if(request.Tools.Count == 0)
+        //     request.Tools = null;
+        // config.MaxOutputTokens = null;
+        
         await _client.SendSetupAsync(new BidiGenerateContentSetup()
         {
             GenerationConfig = config,
-            Model = Model,
+            Model = Model.ToModelId(),
             SystemInstruction = request.SystemInstruction,
             Tools = request.Tools?.ToArray(),
         });

tests/BotSharp.Test.RealtimeVoice/appsettings.json

@@ -27,7 +27,7 @@
       "Models": [
         {
           "Id": "gemini-2.0",
-          "Name": "gemini-2.0-flash-exp",
+          "Name": "gemini-2.0-flash-live-001",
           "Version": "20240620",
           "ApiKey": "",
           "Type": "realtime",
@@ -48,8 +48,11 @@
   },
 
   "RealtimeModel": {
+    "Provider": "google-ai",
+    "Model": "gemini-2.0-flash-live-001",
     "InputAudioFormat": "pcm16",
-    "OutputAudioFormat": "pcm16"
+    "OutputAudioFormat": "pcm16",
+    "InterruptResponse": false,
   },
 
   "PluginLoader": {