Audio Models
Collection
18 items β’ Updated
High-quality English TTS (VITS) optimized for AX650 / AX620E / AX637 NPUs.
| Chip | Encoder | Decoder | Precision |
|---|---|---|---|
| AX650 | NPU (axmodel) | NPU (axmodel) | U16 |
| AX620E | NPU (axmodel) | CPU (onnxruntime) | U16 |
| AX637 | NPU (axmodel) | CPU (onnxruntime) | U16 |
"Hello and welcome to Inflect Micro V2 text to speech."
"The weather today is sunny with a gentle breeze."
"Once upon a time, there lived a curious robot who loved to sing."
"Neural voice synthesis is the next frontier of AI."
"This audio was generated entirely on the AX650 NPU chip."
bash setup.sh
bash run.sh "Hello world." output.wav cli ax650
models/
ax650/ β full NPU (encoder + decoder axmodel)
ax620e/ β encoder axmodel + decoder ONNX
ax637/ β encoder axmodel + decoder ONNX
python/ β Python SDK
cpp/ β C++ SDK
samples/ β audio samples