Skip to content
Trending storyDeveloping

Decagon launches Chord speech model, trained and served on Modal

1 article1 sourcesince Oct 8Last article

Overview

AISummary of 1 article

Decagon Labs has launched Chord, a new speech model, which Modal says was trained and served on its platform.

Modal reports that Chord keeps time-to-first-audio low even during large swings in concurrency.

Decagon says that post-training preserved the model's pace and voice naturalness and raised resolution rates in every deployment. These performance claims come from Modal's announcement and Decagon's statements, and no independent evaluation of them is reported.

Written by AI from the articles below · updated Oct 9, 8:16 AM ET

Check the sources:

Latest developmentOct 8, 4:02 PM ET
Decagon launches Chord, a speech model trained and served on Modal

Article timeline

The articles in this story. Times are ET.

Oct 8
  1. Modal
    Decagon launches Chord, a speech model trained and served on Modal

    AIDecagon Labs has launched Chord, a new speech model, and Modal says it was trained and served on its platform. Modal reports low time-to-first-audio even during large swings in concurrency. Decagon says post-training preserved pace and voice naturalness and raised resolution rates in every deployment.

Heat trend

Not enough continuous observations to show a trend yet.