feat: add Azure OpenAI modality-specific configuration support (#243)

* chore: improve podcast transcripts

* docs: update Azure OpenAI documentation to reflect STT and TTS support

Updated documentation to show that Azure OpenAI now supports all four
modalities (Language, Embedding, STT, TTS) with mode-specific configuration.

Changes:
- Updated Provider Support Matrix table to show Azure supports STT and TTS
- Added recommended STT and TTS models to Azure OpenAI section
- Added clarifying comment for STT and TTS environment variables

Related to modality-specific Azure configuration implementation.

docs/features/ai-models.md

@@ -69,7 +69,7 @@ Open Notebook uses four distinct types of AI models, each optimized for specific
 | **Voyage AI**    | ❌       | ✅        | ❌  | ❌  |
 | **Groq**         | ✅       | ❌        | ✅  | ❌  |
 | **Vertex AI**    | ✅       | ✅        | ❌  | ✅  |
-| **Azure OpenAI** | ✅       | ✅        | ❌  | ❌  |
+| **Azure OpenAI** | ✅       | ✅        | ✅  | ✅  |
 | **OpenRouter**   | ✅       | ❌        | ❌  | ❌  |
 | **Perplexity**   | ✅       | ❌        | ❌  | ❌  |
 | **OpenAI Compatible** | ✅       | ✅        | ✅  | ✅  |
@@ -390,6 +390,8 @@ export AZURE_OPENAI_API_VERSION_EMBEDDING=2024-12-01-preview
 **Recommended Models**
 - **Language**: `gpt-4o`, `gpt-4o-mini`, `gpt-35-turbo`
 - **Embedding**: `text-embedding-3-small`, `text-embedding-ada-002`
+- **STT**: `whisper` (deployment name for Whisper model)
+- **TTS**: `tts`, `tts-hd` (deployment names for TTS models)
 
 **Strengths**
 - Enterprise-grade security and compliance
@@ -587,6 +589,7 @@ export AZURE_OPENAI_API_VERSION_LLM=2024-12-01-preview
 export AZURE_OPENAI_API_KEY_EMBEDDING=your_embedding_key
 export AZURE_OPENAI_ENDPOINT_EMBEDDING=your_embedding_endpoint
 export AZURE_OPENAI_API_VERSION_EMBEDDING=2024-12-01-preview
+# Similarly for _STT and _TTS
 
 # Vertex AI
 export VERTEX_PROJECT=your_project