offline-onnx-speech-rendering

Renders WAV speech locally with a sherpa-onnx VITS/Piper runtime, resolving model, tokens and phonemizer paths and wrapping the offline CLI in a small Node helper. Use when the user says "generate speech offline", "make a WAV of this text", "read this aloud without cloud TTS", or asks to set up or debug sherpa-onnx voice output. Not for streaming/cloud synthesis APIs, speech recognition, or cloning a real person's voice.

Version

v1.0.1

Size

10 KB

Updated

2026-10-06

Your client verifies the signature before reading. This explicit manual read is available on every plan. Free automatically loads five chosen skills; paid plans automatically load relevant skills across the library.