Model · Voice and speech

F5-TTS

A free research text-to-speech model that copies the voice in a short reference clip and reads new text in it. Mainly Chinese and English. Code is open, but the trained model is for non-commercial use only. Needs a technical setup.

Go to F5-TTS’s website

At a glance

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Weights downloadable under CC BY-NC 4.0; code is MIT.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: CC BY-NC 4.0 (weights); MIT (code) (Non-commercial only)
README: models are CC-BY-NC because of the in-the-wild Emilia training data.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: No
Pre-trained weights are non-commercial (CC BY-NC 4.0). The MIT code could be used with weights you train yourself.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Free to download and run; community demo Spaces exist
Plans below.
How you use it: On your own computer, Through another service
Gradio app, command line and Docker image. Hugging Face card says no inference provider deploys it; demo Space is community-run (mrfakename/E2-F5-TTS). Platforms inferred from supported hardware.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
source · checked 12 Oct 2026 · checked on the maker's own page
Made by: SWivid (research team linked to X-LANCE at SJTU, SII and PCL)
README badges link X-LANCE (SJTU), SII and PCL but don't map authors to institutions; no country stated.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Status: Available
Latest README news (12 Mar 2025) announces the v1 Base model; earlier F5TTS_Base and E2TTS_Base checkpoints remain.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

What you can make with it

A voice or speech, read my text aloud (main use)
A voice or speech, a copy of my own voice

text to audioaudio to audio

Takes a reference audio clip plus its transcript and speaks new text; README doesn't use the words 'voice cloning'.

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

Plans and prices

No paid plans listed.

source · checked 12 Oct 2026 · checked on the maker's own page

Rights and safety

Real faces and voices: Copies a real voice (reference clip (zero-shot)), no consent step
Copies the voice in any reference clip you supply; no consent statement in the README or model card.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial

Where you can run it

Hugging Face

Other options for “A voice or speech, read my text aloud”

Adobe Firefly, Akool, Amazon Polly, Arcads, Async (formerly Podcastle), Azure AI Speech, Bark, CAMB.AI, Cartesia, Chatterbox, Clipchamp, Deepgram, DeeVid AI, Descript, Dia, Dubverse, Eleven v3, ElevenLabs, fal, Filmora, Fish Audio, FlexClip, Fliki, getimg.ai

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.