feat: Add standalone WebSocket-only TTS service v1.0.0

feat: Add unmute.sh streaming text processing methodology

fix: Ensure FastAPI endpoints are properly registered v0.2.2

feat: Improve health endpoint with lazy loading explanation v0.2.1

fix: Remove non-existent @spaces.CPU decorator

fix: Ensure @spaces.GPU function detection at module level

fix: Add @spaces.CPU function for Hugging Face Spaces compatibility

fix: Add dummy @spaces.GPU function to satisfy ZeroGPU startup requirements

fix: Display correct wss:// URLs for Hugging Face Spaces in TTS service logs

fix: Correct indentation syntax error in TTS service line 1033

temp: Force WebSocket mode while debugging environment variables

feat: Add clear environment variable logging to TTS service

feat: Add WebSocket support for real-time TTS integration

fix: Add MCP-compatible SafeStream with buffer attribute and stream restoration

fix: Apply comprehensive uvicorn logging protection

fix: Apply bulletproof logging and Gradio fixes

fix: Apply ZeroGPU logging conflict prevention

feat: Complete MCP integration with HTTP fallback v0.3.31

fix: Convert float16 audio to float32 for torchaudio.save() compatibility

trigger: Force rebuild to ensure latest device fixes are deployed

fix: Add comprehensive device handling with CPU fallback for tensor device mismatch

fix: Improve device handling to prevent CUDA/CPU tensor mismatch errors

trigger: Force rebuild with comment update

fix: Add api_name parameter to main prediction function for proper API endpoint

fix: Remove invalid 'every' parameter from iface.load() for Gradio 5.x compatibility

updated grad.io to 5.42.0 to remove some security issues.

fix: Update suggested_hardware to valid zero-a10g

Made changes to accommodate the ZeroGPU.

Initial TTS service deployment

initial commit