How to run F5-TTS locally

SWivid · Voice cloning · 340M params · CC-BY-NC-4.0 (non-commercial)

A flow-matching zero-shot TTS that produces fluent, faithful speech from a short reference clip with strong English/Chinese quality.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 6.0 GB of VRAM (~4-6GB; flow-matching, fast zero-shot cloning), via F5-TTS.
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 SWivid/F5-TTS.

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	Voice cloning
VRAM to run	~6.0 GB (~4-6GB; flow-matching, fast zero-shot cloning)
Download	~1.4 GB
Parameters	340M
License	CC-BY-NC-4.0 (non-commercial)
Run with	F5-TTS

Get F5-TTS 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