Skip to content

fix: Google realtime communication #1009

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Apr 14, 2025
Merged

fix: Google realtime communication #1009

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src/Infrastructure/BotSharp.Core.Realtime/Services/WaveStreamChannel.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
};

Expand Down
10 changes: 7 additions & 3 deletions src/Plugins/BotSharp.Plugin.GoogleAI/Providers/Realtime/RealTimeCompletionProvider.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,7 +79,7 @@ public async Task Connect(RealtimeHubConnection conn,

await AttachEvents(_client);

await _client.ConnectAsync();
await _client.ConnectAsync(false);
}

public async Task Disconnect()
Expand All @@ -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)
Expand Down Expand Up @@ -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(),
});
Expand Down
7 changes: 5 additions & 2 deletions tests/BotSharp.Test.RealtimeVoice/appsettings.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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",
Expand All @@ -48,8 +48,11 @@
},

"RealtimeModel": {
"Provider": "google-ai",
"Model": "gemini-2.0-flash-live-001",
"InputAudioFormat": "pcm16",
"OutputAudioFormat": "pcm16"
"OutputAudioFormat": "pcm16",
"InterruptResponse": false,
},

"PluginLoader": {
Expand Down
Loading