Inflect TTS v2+ONNX, 9M/4M text-to-speech models running in the browser

Inflect TTS v2 offers 9M and 4M parameter text-to-speech models that run directly in the browser using ONNX runtime. The models convert text to speech client-side without requiring a server or API calls. Two model sizes are available to balance quality and performance depending on the use case.