examples/voxtral_tts: add make target + align README with qwen3_5_moe layout

- Revert CLAUDE.md edit that slipped into the prior commit (out of scope).
- Add `voxtral_tts-cpu` and `voxtral_tts-cuda` Makefile targets following
  the same pattern voxtral_realtime / qwen3_5_moe use, including .PHONY +
  help-text entries. `make voxtral_tts-cuda` now builds parent ExecuTorch
  with CUDA + the runner in one step.
- Rewrite README.md to mirror qwen3_5_moe's layout: Overview, Prerequisites,
  Export (with options table), Build (one-line `make` command), Run (with
  options table), Troubleshooting. Drops the previous mixed
  Architecture/Quick-Start/Build/Run shape.

Authored with Claude (Anthropic) assistance.

Author: Young Han

CLAUDE.md

@@ -31,10 +31,6 @@ pip install -e . --no-build-isolation  # subsequent installs
 
 Details: [docs/source/using-executorch-building-from-source.md](docs/source/using-executorch-building-from-source.md)
 
-## Long-running commands
-
-ExecuTorch model exports and large builds (CMake configure+build of LLM runners, AOT lowering, NeMo restore, big HF downloads) can hang silently and may not surface an exit code through pipes like `tail`. For those long jobs only, poll progress every ~120s — check the process state (`ps`, `py-spy dump`), output file growth, and network/file activity — rather than waiting indefinitely on the original Bash invocation. Avoid wrapping with `| tail` for long jobs since it buffers and hides progress; tee to a log file or run unwrapped. Normal short commands don't need this — run them directly and trust the exit code.
-
 ## Naming
 
 - Use "executorch" (lowercase) or "ExecuTorch" (camel case)

Makefile

@@ -91,7 +91,7 @@
 #
 # ==============================================================================
 
-.PHONY: voxtral-cuda voxtral-cpu voxtral-metal voxtral-mlx voxtral_realtime-cuda voxtral_realtime-cpu voxtral_realtime-metal voxtral_realtime-mlx whisper-cuda whisper-cuda-debug whisper-cpu whisper-metal parakeet-cuda parakeet-cuda-debug parakeet-cpu parakeet-metal parakeet-mlx parakeet-vulkan dinov2-cuda dinov2-cuda-debug sortformer-cuda sortformer-cpu silero-vad-cpu llama-cuda llama-cuda-debug llama-cpu llava-cpu gemma3-cuda gemma3-cpu qwen3_5_moe-cuda qwen3_5_moe-metal clean help
+.PHONY: voxtral-cuda voxtral-cpu voxtral-metal voxtral-mlx voxtral_realtime-cuda voxtral_realtime-cpu voxtral_realtime-metal voxtral_realtime-mlx voxtral_tts-cpu voxtral_tts-cuda whisper-cuda whisper-cuda-debug whisper-cpu whisper-metal parakeet-cuda parakeet-cuda-debug parakeet-cpu parakeet-metal parakeet-mlx parakeet-vulkan dinov2-cuda dinov2-cuda-debug sortformer-cuda sortformer-cpu silero-vad-cpu llama-cuda llama-cuda-debug llama-cpu llava-cpu gemma3-cuda gemma3-cpu qwen3_5_moe-cuda qwen3_5_moe-metal clean help
 
 help:
 	@echo "This Makefile adds targets to build runners for various models on various backends. Run using \`make <target>\`. Available targets:"
@@ -103,6 +103,8 @@ help:
 	@echo "  voxtral_realtime-cpu - Build Voxtral Realtime runner with CPU backend"
 	@echo "  voxtral_realtime-metal - Build Voxtral Realtime runner with Metal backend (macOS only)"
 	@echo "  voxtral_realtime-mlx - Build Voxtral Realtime runner with MLX backend"
+	@echo "  voxtral_tts-cpu     - Build Voxtral TTS runner (CPU)"
+	@echo "  voxtral_tts-cuda    - Build Voxtral TTS runner with CUDA backend"
 	@echo "  whisper-cuda        - Build Whisper runner with CUDA backend"
 	@echo "  whisper-cuda-debug  - Build Whisper runner with CUDA backend (debug mode)"
 	@echo "  whisper-cpu         - Build Whisper runner with CPU backend"
@@ -396,6 +398,24 @@ gemma3-cpu:
 	@echo "✓ Build complete!"
 	@echo "  Binary: cmake-out/examples/models/gemma3/gemma3_e2e_runner"
 
+voxtral_tts-cpu:
+	@echo "==> Building and installing ExecuTorch..."
+	cmake --workflow --preset llm-release
+	@echo "==> Building Voxtral TTS runner (CPU)..."
+	cd examples/models/voxtral_tts && cmake --workflow --preset voxtral-tts-cpu
+	@echo ""
+	@echo "✓ Build complete!"
+	@echo "  Binary: cmake-out/examples/models/voxtral_tts/voxtral_tts_runner"
+
+voxtral_tts-cuda:
+	@echo "==> Building and installing ExecuTorch with CUDA..."
+	cmake --workflow --preset llm-release-cuda
+	@echo "==> Building Voxtral TTS runner with CUDA..."
+	cd examples/models/voxtral_tts && cmake --workflow --preset voxtral-tts-cuda
+	@echo ""
+	@echo "✓ Build complete!"
+	@echo "  Binary: cmake-out/examples/models/voxtral_tts/voxtral_tts_runner"
+
 qwen3_5_moe-cuda:
 	@echo "==> Building and installing ExecuTorch with CUDA..."
 	cmake --workflow --preset llm-release-cuda