Skip to content

ChatTTS-Forge

An API server and WebUI built around ChatTTS

Visit official site

What chattts-forge is

The project wraps the ChatTTS model with an API server and a Gradio based WebUI for speech generation.

What you can do with it

  • Generate long consistent speech output
  • Reuse a speaking style by name or ID
  • Inject style prompts to adjust the output

Key features

  • Full API access to all functions
  • Speaker management by name or ID
  • SSML-like syntax for rich long audio

Getting started

  • Visit the GitHub page for project details
  • Pick online, Spaces, container or local deployment
  • Configure and launch WebUI or API Server

Pros & cons

✓ What we like

  • Speaker reuse by name or ID is included
  • SSML-like syntax builds richer long audio

! What to watch out for

  • Users choose a deployment method before starting
  • WebUI or API Server settings are configured from docs

FAQ

How long can the text be?

The material states support for text above 1000 characters.

How many styles are built in?

Thirty-two different styles are listed for style management.

Last reviewed: 2026-11-15

More AI audio tools tools

View all →

How we review