Skip to content
Trending storyDeveloping

Drama-3 added to Hugging Face speech-to-speech as open-source pull request

1 article1 sourcesince Oct 19Last article 2h ago ·

Overview

AISummary of 1 article

Jack Boylan adds Fish Audio's Drama-3 model to the Hugging Face speech-to-speech project, according to a post by Thomas Wolf, who owns the Hugging Face account on X. Wolf praises the open-source release.

Boylan says the integration lets him clone his voice so it can whisper, laugh, sigh, or sound worried on request.

The integration is offered as a pull request on the Hugging Face speech-to-speech GitHub repository, not as a merged feature.

Written by AI from the articles below · updated Oct 19, 5:15 PM ET

Check the sources:

Latest developmentOct 19, 5:02 PM ET
Thomas Wolf praises open-source Fish Audio Drama-3 speech-to-speech demo

Article timeline

The articles in this story. Times are ET.

Oct 19
  1. Thomas WolfX
    Thomas Wolf praises open-source Fish Audio Drama-3 speech-to-speech demo

    AIThomas Wolf, who owns the Hugging Face account, praises the open-source release of the speech-to-speech project. Jack Boylan adds Fish Audio's Drama-3 to speech-to-speech, cloning his voice so it can whisper, laugh, sigh, or sound worried on request. The integration is available in a pull request on the Hugging Face speech-to-speech GitHub repository.

Heat Trend

Not enough continuous observations to show a trend yet.