feat: add iOS TTS support using ONNX Runtime

[AnthonyRonning]

Summary

Add Text-to-Speech (TTS) support for iOS using ONNX Runtime, enabling the Supertonic TTS model to run on-device on iPhones and iPads.

Changes

• Cargo.toml: Add iOS-specific dependencies for ort and other TTS libraries
• build.rs: Add iOS-specific linker configuration for ONNX Runtime xcframework
• lib.rs: Enable TTS module for iOS (was desktop-only), add TTS commands to iOS invoke handler
• tts.rs: Add iOS-specific path handling for TTS model storage (~/Documents/tts_models)
• TTSContext.tsx: Update frontend to enable TTS on iOS
• GitHub Actions: Add steps to download ONNX Runtime xcframework before iOS builds
• setup-ios-onnxruntime.sh: New script to download pre-built ONNX Runtime 1.20.1 xcframework

Technical Details

• Uses pre-built ONNX Runtime 1.20.1 xcframework from csukuangfj/ios-onnxruntime on HuggingFace
• Static libraries are cached in GitHub Actions to speed up builds
• TTS models (~264MB) are downloaded on-demand, same as desktop
• Memory usage ~500MB RAM, suitable for modern iOS devices

Testing

• Test on iOS simulator
• Test on physical iOS device
• Verify model download works on iOS
• Verify TTS playback works on iOS

Notes

This is the first step toward iOS TTS. The implementation mirrors the desktop version - users will need to download the TTS models (~264MB) before use.

Summary by CodeRabbit

• New Features

  • TTS now available on iOS with dedicated app initialization, deep-link handling, updater integration, and iOS-specific model/engine management.
  • UI surfaces TTS playback errors via notifications; TTS context exposes lastPlaybackError for apps to consume.

• Chores

  • Enhanced iOS build and deployment pipeline: caching with build-from-source fallback, artifact verification, generated link configuration, runtime library propagation, and TestFlight trigger adjustments.

_{✏️ Tip: You can customize this high-level summary in your review settings.}