Switch AI backend from OpenAI GPT-3.5 to Google Gemini

[Copilot]

Replaces the OpenAI GPT-3.5 Turbo integration with Google's Gemini API (gemini-2.0-flash) using the official Google.GenAI SDK.

Changes

• TalkGPT.csproj: Swap Betalgo.OpenAI.GPT3 → Google.GenAI v1.2.0
• talkgptsettings.json: Rename config key OpenAI_APIKEY → Gemini_APIKEY
• Program.cs:
  • Replace OpenAI imports and OpenAIService with Google.GenAI.Client
  • Instantiate Client once outside the recognition loop (was re-created per request)
  • Add fallback console message when Gemini returns no candidates

var geminiClient = new Client(apiKey: Gemini_APIKey);
// ...
var response = await geminiClient.Models.GenerateContentAsync(
    model: "gemini-2.0-flash",
    contents: text
);
if (response?.Candidates?.Count > 0)
{
    geminiResult = response.Candidates[0].Content?.Parts?[0]?.Text ?? "";
    // speak geminiResult ...
}
else
{
    Console.WriteLine("\nTalkGPT = (No response received from Gemini)");
}

Note: The Gemini_APIKEY value in talkgptsettings.json must be replaced with a valid key from Google AI Studio before use.

Original prompt

---

This section details on the original issue you should resolve

<issue_title>我要把AI 模型改為GEMINI 的AI模型</issue_title>
<issue_description>我要把AI 模型改為GEMINI 的AI模型
KEY = 123123123</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes 我要把AI 模型改為GEMINI 的AI模型 #5

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

[Copilot]

Copilot wasn't able to review any files in this pull request.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.