Analyzing, transcribing, generating, or understanding audio and speech signals.
3 models
by Suno
A high-fidelity text-to-speech model with expressive voice generation in multiple languages.
Not yet ratedby Mozilla
An open-source speech-to-text engine based on Baidu's Deep Speech research.
Not yet ratedby OpenAI
A general-purpose speech recognition model that transcribes and translates audio in many languages.
Not yet rated