Skip to content

ChatTTS_Speaker

Score and label voice timbre stability

Visit official site

What ChatTTS_Speaker is

ChatTTS_Speaker is an experimental open source project built on the ERes2NetV2 speaker recognition model. It scores timbre stability and adds labels to help users choose voices.

What you can do with it

  • Score timbre stability across sentence lengths
  • Predict gender, age and voice traits
  • Listen online and download samples

Getting started

  • Visit the project page and read the docs
  • Listen to samples online
  • Download the chosen sample file

Pros & cons

✓ What we like

  • The project is open source and community driven
  • Samples are shown on two model hubs

! What to watch out for

  • The project is described as experimental
  • Use is centred on timbre sample files

FAQ

Which model is it based on?

The ERes2NetV2 speaker recognition model.

What can be downloaded?

Voice timbre sample files.

Last reviewed: 2026-11-15

More AI audio tools tools

View all →

How we review