feat(api): add OpenAI-compatible ASR transcription endpoint

- Implement POST /audio/transcriptions and /v1/audio/transcriptions
  endpoints for automatic speech recognition
- Add support for multipart/form-data audio file uploads
- Support multiple audio formats (wav, mp3, m4a, etc.)
- Implement language detection with 29 supported languages
- Return transcription text in OpenAI-compatible JSON format
- Add proper error handling and validation
- Include comprehensive tests for ASR functionality

refactor(api): restructure API modules and export MODEL

- Move API declarations to src/api/mod.rs
- Add ASR module and type definitions
- Export MODEL static for use in ASR module
- Mount ASR routes at both /audio and /v1/audio endpoints

Makefile

@@ -14,6 +14,14 @@ build_mac:
 	@echo "Building project for macOS..."
 	@cargo build --features metal  --release
 
+build_mac_universal:
+	@echo "Building universal binary for macOS..."
+	@cargo build --features metal --release --target aarch64-apple-darwin
+	@cargo build --features metal --release --target x86_64-apple-darwin
+	@mkdir -p target/universal/release
+	@lipo -create target/aarch64-apple-darwin/release/aha target/x86_64-apple-darwin/release/aha -output target/universal/release/aha
+
+
 test:
 	@echo "Running tests..."
 	@cargo test