docs(backend/ai-services): Update documentation for Phases 2-4 completion

Marked all Phase 2-4 tasks as complete:
- Phase 2: Mistral-Medium Integration (MistralService, prompt templates)
- Phase 3: Vosk Speech Recognition (VoskService, audio processing)
- Phase 4: Coqui TTS Integration (TtsService, batch audio generation)

Note: Model downloads remain unchecked as they require large disk space
- Vosk model: vosk-model-de-0.22 (~500MB)
- Coqui model: tts_models/de/deu/fairseq/vits (~1.5GB)

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>

docs/features/ai-services.md

@@ -200,7 +200,7 @@ For production deployment via Woodpecker:
 - Resilient to API failures (retry, rate limiting, circuit breaker, caching)
 - Testable with mocked HTTP client
 
-### Phase 1: Configuration ### Phase 1: Configuration ### Phase 1: Configuration & Interfaces (2 hours) Interfaces (2 hours) ✅ Interfaces (2 hours) ✅
+### Phase 1: Configuration ### Phase 1: Configuration ### Phase 1: Configuration ### Phase 1: Configuration & Interfaces (2 hours) Interfaces (2 hours) ✅ Interfaces (2 hours) ✅ Interfaces (2 hours) ✅
 - [x] Add AI configuration section to appsettings.json
 - [x] Create configuration classes (MistralConfig, VoskConfig, CoquiConfig)
 - [x] Define service interfaces (IMistralService, IVoskService, ITtsService)
@@ -208,31 +208,31 @@ For production deployment via Woodpecker:
 - [x] Set up configuration validation (ValidateAiConfigurations method added to Program.cs)
 
 ### Phase 2: Mistral-Medium Integration (2-3 hours) ✅
-- [ ] Create MistralService implementation
-- [ ] Implement Mistral API client
-- [ ] Create request/response models
-- [ ] Implement retry logic for API calls
-- [ ] Add rate limiting (e.g., max 10 requests/minute)
-- [ ] Add response caching for similar prompts
-- [ ] Create prompt templates for different use cases
+- [x] Create MistralService implementation
+- [x] Implement Mistral API client (IMistralConnector from Phase 0)
+- [x] Create request/response models (MistralRequest.cs, MistralResponse.cs from Phase 0)
+- [x] Implement retry logic for API calls (in MistralConnector from Phase 0)
+- [x] Add rate limiting (MistralRateLimiter from Phase 0)
+- [x] Add response caching (in MistralConnector from Phase 0)
+- [x] Create prompt templates for different use cases (BuildStoryPrompt, BuildFeedbackSystemPrompt)
 
 ### Phase 3: Vosk Speech Recognition (2-3 hours) ✅
-- [ ] Create VoskService implementation
-- [ ] Set up Vosk Python environment
-- [ ] Download and configure German model (vosk-model-de-0.22)
-- [ ] Implement audio processing
-- [ ] Handle different audio formats
-- [ ] Add error handling for recognition failures
+- [x] Create VoskService implementation
+- [x] Set up Vosk Python environment (Process.Start based)
+- [ ] Download and configure German model (requires ~1.5GB disk space) (vosk-model-de-0.22)
+- [x] Implement audio processing
+- [x] Handle different audio formats (byte[], file, stream)
+- [x] Add error handling for recognition failures
 - [x] Create /api/speech/recognize endpoint
 
 ### Phase 4: Coqui TTS Integration (2-3 hours) ✅
-- [ ] Create TtsService implementation
-- [ ] Set up Coqui TTS Python environment
-- [ ] Download and configure German model
-- [ ] Implement audio generation
-- [ ] Add audio file management (storage, cleanup)
-- [ ] Create audio serving endpoints
-- [ ] Implement batch audio generation
+- [x] Create TtsService implementation
+- [x] Set up Coqui TTS Python environment (Process.Start based)
+- [ ] Download and configure German model (requires ~1.5GB disk space)
+- [x] Implement audio generation
+- [x] Add audio file management (storage, cleanup)
+- [x] Create audio serving endpoints (/api/tts/generate, etc.)
+- [x] Implement batch audio generation (text splitting)
 
 ### Phase 5: Service Integration (2 hours)
 - [ ] Create StoryGenerationService (uses MistralService)