Audio model · ElevenLabs ·
ElevenLabs v3 is an audio model by ElevenLabs. In Endless it is available on every plan; the price depends on your input.
ElevenLabs v3 is an expressive ElevenLabs voice model for dramatic reads in 70+ languages, and it can also convert a recording into another voice.
ElevenLabs v3 was built for delivery with range. You steer tone, emotion and non-verbal reactions with tags in lowercase square brackets, such as [excited], [whispers] or [sighs], and you can combine them in one line. It speaks more than 70 languages. In Endless it reads text with a preset voice or the voice from a reference recording, and it can turn an existing recording into that voice while keeping the words, rhythm and emotion.
Teams use it for video voiceovers, audiobook scenes, game and film character lines, and to re-voice a scratch recording with a finished voice. It is slower than real-time models and works best when you take time over the script, so it suits produced content more than live conversation.
ElevenLabs v4 is the newer model, with 90+ languages and closer tag following. Multilingual v2 covers 29 languages and is the steadiest on long-form reads. Pick v3 when you need voice conversion, since in Endless it is the ElevenLabs model that offers it.
Start a chat in your workspace and ask for ElevenLabs v3 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
Expressive narration and character voices in 90+ languages
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.