Place to run it · Pictures, Video, Voice and speech, Music and sound, Talking presenters, 3D

Hugging Face

The main public library of AI models, where makers publish open models for pictures, video, speech, music and 3D. You can download them, try many in free browser demos (Spaces), or pay to run them on rented computers.

Go to Hugging Face’s website

At a glance

Can I sell what I make?: Depends on the model you choose
Terms: you own the Content you create; other users' content is used at your own risk under its own terms. Commercial use of outputs depends on each model's licence.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Free account; ZeroGPU Spaces at 5 minutes of GPU a day (2 without an account); free CPU Basic hardware
Plans below.
How you use it: In your browser, Maker's own API, On your own computer
Browser demos (Spaces), paid inference API and endpoints, and model downloads to run yourself.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Some setup
Trying a Space needs no setup; downloading or hosting models is technical.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review
Made by: Hugging Face, Inc. (US)
Terms describe Hugging Face, Inc. as a Delaware corporation; no street address in the terms. Country taken from place of incorporation.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Status: Available
source · checked 12 Oct 2026 · checked on the maker's own page

What you can make with it

A voice or speech, text from a recording (main use)
A picture, from a description
A voice or speech, read my text aloud
A video, from a description
A 3D object or scene, from a photo

text to imagetext to audioaudio to texttext to videoimage to 3D model

Hosts thousands of models across every area; a representative pick of what people mainly use it for. 'Main' is arbitrary for a general host.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Plans and prices

Plan	Price	Includes
PRO	$9 a month	2,400 seconds of computer time a day 40 minutes of ZeroGPU a day plus $2 inference credits a month; extra GPU $1 per 10 minutes
Team	$20 a month	Per user; members get PRO-level ZeroGPU and inference benefits
Enterprise	$50 a month	Per user; 60 minutes of ZeroGPU a day
Spaces GPU: Nvidia T4 small	$0.40 per 3600 seconds of computer time	Per hour of rented 16 GB GPU
Spaces GPU: Nvidia A100 large	$2.50 per 3600 seconds of computer time	Per hour of rented 80 GB GPU

Some plans are not listed here; see the source for the full list.

Carried over from pilot (read 2026-10-12); could not be re-read in this pass (fetch budget). Page shows '$' without naming USD. ZeroGPU quotas from https://huggingface.co/docs/hub/spaces-zerogpu. Inference Endpoints from $0.033/hour. Billing cadence of Team/Enterprise not re-checked.

source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Rights and safety

Trains on your work?: The terms don't say clearly
Terms don't mention training; Hugging Face won't sell content and may learn from aggregated, anonymised usage data. Privacy policy not read.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Models you can run here

Bark, BiRefNet, Chatterbox, CogVideoX, Dia, Distil-Whisper, FLUX.1 [dev], FLUX.1 [schnell], HiDream-I1, HunyuanVideo, Hunyuan3D 2, Kokoro-82M, LTX-Video, MAGI-1, Mochi 1, NVIDIA Parakeet, Open-Sora, Whisper, OpenAudio S1, Qwen-Image, RVC (Retrieval-based Voice Conversion), Stable Diffusion XL 1.0, Sesame CSM, SkyReels V2, Stable Audio Open 1.0, Stable Diffusion 3.5, Stable Video Diffusion, Wan 2.1, Wan 2.2, XTTS-v2

Other options for “A voice or speech, text from a recording”

Adobe Podcast (Enhance Speech), Adobe Premiere, AssemblyAI, Async (formerly Podcastle), AudioShake, Auphonic, Azure AI Speech, CAMB.AI, Cartesia, Cleanvoice AI, Clipchamp, Deepgram, Descript, Distil-Whisper, Dubverse, ElevenLabs, Filmora, Gling, Happy Scribe, Kapwing, Krisp, MacWhisper, MiniMax Audio, Narakeet

About this entry

Facts last checked 12 Oct 2026 against the maker’s own pages (each fact links to its source). Entry status: draft. Plain-English summary written by Plainly.