Skip to content

Automatic push to talk feature. #2

Description

@slategraydev

I have an idea for an automated push to talk feature, leveraging the "biometric speech identification" models I've seen floating around.

Honestly I could probably implement this myself. Grab a high quality voice embedding pipeline, have a "enrollment" phrase (like Sphinx of Black Quartz...) and grab vectors for the speaker, then continuously check audio chunks for those vectors.

Metadata

Metadata

Assignees

Labels

featureNew feature or request

Projects

No projects

Relationships

None yet

Development

No branches or pull requests

Issue actions