Audio model · ElevenLabs ·
ElevenLabs v4 is an audio model by ElevenLabs. In Endless it is available on every plan; the price depends on your input.
ElevenLabs v4 is the newest ElevenLabs voice model, built for expressive narration, dialogue and character work in more than 90 languages.
ElevenLabs v4, released in September 2026, is the most expressive voice model ElevenLabs offers. You direct the read with inline tags for emotion and sound effects, such as [laughs] or [light rain], and the model follows them more closely than earlier versions. It speaks more than 90 languages, and a voice recorded in one language keeps its identity when it speaks another, with stronger accent adherence.
In Endless you pick a preset voice or upload a reference recording, then paste the text. Teams use it for audiobook chapters, character dialogue for games and animation, ad voiceovers and localized versions of the same script. Speaker identity stays consistent across regenerated lines, which matters when you fix one sentence in a long take.
ElevenLabs v3 is the previous generation, with 70+ languages and a voice conversion mode. Multilingual v2 covers 29 languages and gives you stability and style sliders. All three run from the same workspace credits, so you can compare takes in chat or on the canvas.
Start a chat in your workspace and ask for ElevenLabs v4 by name.
Paste your script or describe the sound, its tone and its length.
Ask for another take or a different voice. Every clip is saved to your workspace assets.
by ElevenLabs
Dramatic voice reads directed with audio tags, plus voice conversion
Price depends on your input
by ElevenLabs
Steady long-form narration in 29 languages with fine voice control
From 1 credit per clip
by MiniMax
Voiceovers with laughs, sighs and pauses written into the script
From 1 credit per clip
Start free, create a project, and bring your brand’s references together. Or book a demo to explore Endless with your team.