Back to model community

Speech Transcription - powered by Modzy MLOps platform for Enterprise and Edge AI

Speech Transcription

Model by Open Source

This model can convert a piece of text into an audio file. It accepts a string of UTF-8 text as the input. The model returns a WAV audio file that is an audio version of the text input file. This model can be used for call center automation, interactive responses from IoT devices, or transforming text to be consumed as audio, for example while driving or for the visually impaired.

See the model in action with a Modzy MLOps platform demo or start a trial