Sign in to access this content and additional site features.
This demo showcases Text To Speech on MCU i.MXRT700 and i.MX8M and i.MX9 MPU family. Speech synthesis can be used for enabling AI assistants and enhancing user experiences. For MPU, the TTS model is based on VITS architecture (Variational Inference with adversarial learning for end-to-end Text-to-Speech paper). Depending on the language, there may be several speakers, male or female, different accents and tones of voice. The frequency sampling rate is 16kHz or 22kHz depending on the model. For MCU i.MXRT700, the TTS model relies on the NPU.
Learn more about NXP's voice solutions and contact us at voice@nxp.com