Voxta docs
Voxta ServerServicesText-to-Speech

Chatterbox TTS

Chatterbox TTS is a local diffusion-transformer text-to-speech engine for Voxta. Voxta installs the runtime and weights on first use.

Chatterbox TTS is a local text-to-speech engine using a Diffusion Transformer with ConvNeXt V2 — faster training and inference than older diffusion TTS models.

Setup

Add the service

Manage Modules → Add Modules → Chatterbox TTS → Install. Voxta installs the Python runtime and model weights automatically (watch the Terminal for first-run install progress).

Pick a voice

In the Chatterbox config, browse available voices and pick one.

Orpheus

LLM-based TTS by Canopy Labs that produces emotive, expressive speech with natural disfluencies.

XTTS (Coqui)

XTTS (Coqui) is an open-source local text-to-speech engine for Voxta with multilingual output and voice cloning from short reference clips.

On this page

SetupAdd the servicePick a voice