How to run Chatterbox locally

Resemble AI · Text → speech · 500M params · MIT (commercial OK)

A production-grade open TTS with zero-shot voice cloning and unique emotion-exaggeration control, often preferred over closed services in blind tests.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 8.0 GB of VRAM (~8GB; runs on RTX 3060-class GPUs), via Chatterbox / Transformers.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at ResembleAI/chatterbox.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → speech
VRAM to run	~8.0 GB (~8GB; runs on RTX 3060-class GPUs)
Download	~2 GB
Parameters	500M
License	MIT (commercial use OK)
Run with	Chatterbox / Transformers

Get Chatterbox on Hugging Face →

More voice & audio models

Whisper large-v3 — Speech → text, ~10 GB VRAM
Whisper large-v3-turbo — Speech → text, ~6.0 GB VRAM
Kokoro-82M — Text → speech, ~1.0 GB VRAM
XTTS-v2 — Voice cloning, ~6.0 GB VRAM
MusicGen Large — Text → music, ~16 GB VRAM
Parakeet TDT 0.6B v2 — Speech → text, ~4.0 GB VRAM

Browse: all media models · chat / LLM models