Model · Voice and speech

Eleven v3

ElevenLabs' expressive text-to-speech model. It reads text aloud in 70+ languages, and you can steer emotion and delivery with tags in the text or write multi-speaker dialogue. Only usable through ElevenLabs' app and API.

Go to Eleven v3’s website

At a glance

Open or closed: Closed
Only usable through the maker's app or API
No downloadable weights; app and API only.
source · checked 12 Oct 2026 · checked on the maker's own page
Licence: ElevenLabs Terms of Service (The maker's own terms)
source · checked 12 Oct 2026 · checked on the maker's own page
Can I sell what I make?: Yes, on paid plans
Terms 1(c): free users non-commercial only; paid users may use commercially, subject to the Prohibited Use Policy.
source · checked 12 Oct 2026 · checked on the maker's own page
Cost: Free option: Usable on ElevenLabs' free plan (non-commercial)
Plans below.
How you use it: In your browser, Phone app, Maker's own API
API model id eleven_v3; works with Text to Speech and Text to Dialogue APIs.
source · checked 12 Oct 2026 · checked on the maker's own page
Skill needed: No setup
In the ElevenLabs app; API use is technical.
source · checked 12 Oct 2026 · checked, but the page was unclear or partial
Made by: Eleven Labs Inc. (US)
Terms 12(c), 16(d): New York address.
source · checked 12 Oct 2026 · checked on the maker's own page
Status: Available
Model docs now call it a 'previous generation' model; still offered via API. A separate realtime 'Eleven v3 Conversational' exists.
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)

text to audio

Audio tags for emotion and delivery; Dialogue Mode for several speakers.

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

Plans and prices

No paid plans listed.

No v3-specific price on the pages read; billed through ElevenLabs credits (see the elevenlabs entry).

source · checked 12 Oct 2026 · inferred or from a secondary source; needs review

Rights and safety

Trains on your work?: Trains on your work unless you opt out
Terms 4(d), 4(i): content may be used to improve services and models; opt out in 'Data use' settings.
source · checked 12 Oct 2026 · checked on the maker's own page
Limits: note: 5,000 characters per request (about 5 minutes of audio)
source · checked 12 Oct 2026 · checked on the maker's own page

Where you can run it

ElevenLabs

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, ElevenLabs, F5-TTS, 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.