What is Speech-to-speech model?

Speech-to-speech model

Speech-to-speech model: A model that takes audio in and produces audio out without an intermediate text step, preserving tone, timing and interruption.

Related terms

Automatic speech recognition (ASR)
Autoregressive model
Cascade (model cascade)
Consistency model
Denoising diffusion implicit model (DDIM)
Denoising diffusion probabilistic model (DDPM)
Diffusion model
Distillation of a frontier model

Browse the full glossary →