Model · Voice and speech

XTTS-v2

A downloadable text-to-speech model that reads text aloud in 17 languages and can copy a voice from a 6-second clip. Its licence allows non-commercial use only, including what you make with it. Needs technical setup.

Go to XTTS-v2’s website

At a glance

Open or closed: Downloadable, with conditions
You can download and run it, but the licence limits use
Downloadable under the Coqui Public Model License, which is non-commercial.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: Coqui Public Model License (CPML) (Non-commercial only)
Card links coqui.ai/cpml; the copy in the repository was read.
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: No
Licence: 'allows only non-commercial use of a machine learning model and its outputs'; no payment may arise from use of the model or its output.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Free to download; you pay for your own hardware
Plans below.
How you use it: On your own computer, Through another service
Run with the Coqui TTS Python library; weights on Hugging Face.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Skill needed: Technical
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Coqui.ai
Model card names Coqui.ai; no country stated, and the licence names no licensor.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
Weights still downloadable. coqui.ai could not be fetched, so the maker's current status was not verified; the card says nothing about it.
source · checked 12 Oct 2026 · inferred or from a secondary source; needs review

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

Voice cloning from a 6-second clip; cross-language cloning.

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

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 (6-second reference clip), no consent step
Any short clip can be used; no consent step in the model.
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, F5-TTS, fal, Filmora, Fish Audio, FlexClip, Fliki

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.