How to run StyleTTS 2 locally

yl4579 · Text → speech · 90M params · MIT (code); weights require synthetic-disclosure + consent (non-commercial)

A style-diffusion TTS reaching human-level quality on LibriTTS that underpins many downstream models (including Kokoro's lineage).

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 2.0 GB of VRAM (Light; runs comfortably under ~2GB VRAM), via StyleTTS2.
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 yl4579/StyleTTS2-LibriTTS.

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	~2.0 GB (Light; runs comfortably under ~2GB VRAM)
Download	~0.7 GB
Parameters	90M
License	MIT (code); weights require synthetic-disclosure + consent (non-commercial)
Run with	StyleTTS2

Get StyleTTS 2 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
Chatterbox — Text → speech, ~8.0 GB VRAM

Browse: all media models · chat / LLM models