6 GB NVIDIA memory
FP32 · Chatterbox runtime
The official implementation uses CUDA when available; this is a practical provider baseline with room for synthesis.
Resemble AI
Audio model
Chatterbox
An expressive English speech model with zero-shot voice cloning from Resemble AI.
Speech
Capabilities
What you can use it for.
The most useful reasons to choose this model, without making you read through its repository first.
Text to speechVoice cloningExpressive deliveryOpen weights
01
Voice cloning
02
Narration
03
Expressive assistants
For providers
Want to serve this model?
The provider requirements live here, separate from the information you need to choose and use the model.
Starting point6 GB GPU memory
Conservative estimate
Source and license
Check the original model.
OpenMayhem links back to the source repository so you can inspect the model card, files, license, limitations, and creator guidance directly.
