Announcement
Gradium's latest text-to-speech model reportedly leads Voice Arena's US English latency board
Gradium says the model's median time to first audio is under 100 milliseconds, down from 236 milliseconds for its previous model.
TLDR
On October 6, Gradium said its latest text-to-speech model, released two weeks earlier, still led Voice Arena's US English latency board. The company put its median time to first audio at under 100 milliseconds, compared with 236 milliseconds for its previous model.
Combined views
1.5K
2 Sources, first seen ago