Skip to content
Log inSign up free

Audio model by ElevenLabs

ElevenLabs v4 AI audio generator

ElevenLabs' most expressive text to speech, directed line by line with audio tags.

Try Eleven v4See the prompt guide

No installation. No credit card. Private by default.

At a glance

ElevenLabs v4 is ElevenLabs's audio model, run by ElevenLabs and reached through Mage. On Mage it makes audio from a prompt. It costs from 30 Gems (about $0.03) per 250 characters and runs unlimited from the Basic plan, and new accounts get 300 free Gems to start.

  • 30Gems per 250 characters, from
  • $0.03About, in US dollars
  • BasicUnlimited from

Overview

What is ElevenLabs v4?

Eleven Speech is ElevenLabs' text to speech on Mage, running its latest model, Eleven v4. It reads your text in a choice of voices and more than 90 languages, with the emotion, timing, and breath of a real performance.

Audio tags in square brackets direct the performance: a whisper, a laugh, a sarcastic aside, a door slamming in the background.

It runs in the same account as your images and videos, and it is unlimited on paid plans up to a length each plan sets.

Samples

Made with ElevenLabs v4

Generated on Mage with Eleven v4. A prompt under a sample is the exact prompt that made it.

  • A whisper, excitement, and a laugh in one line

    Prompt: [whispers] Did you hear that? [excited] It is them. They actually came back! [laughs] I knew it.

  • A storyteller narrator

    Prompt: Every lighthouse keeps one promise... to stay lit until morning. [softly] And this one never broke it.

  • Spanish, warm and playful

    Prompt: [warmly] Bienvenidos a la cocina de mi abuela. Hoy preparamos churros... [laughs] y sí, nos vamos a comer la mitad antes de terminar.

  • Japanese, a calm station announcement

    Prompt: [calmly] 次は、京都です。お出口は右側です。[softly] 本日もご乗車いただき、ありがとうございました。

  • A product voiceover

    Prompt: Meet the bottle that keeps coffee hot for twelve hours... and water cold for a full day. [confident] One bottle. Every adventure.

  • A game character under pressure

    Prompt: [shouting] Hold the line! [panting] They're coming over the wall... [determined, low voice] Not today. Not while I'm standing.

  • A sound cue inside the speech

    Prompt: [door creaks] Pull up a chair... [softly] the fire's still warm. Tonight's story begins on a road nobody takes after dark.

  • French, from enthusiasm to a whisper

    Prompt: [enthusiastic] Bonjour à tous ! Aujourd'hui, on part à la découverte des marchés de Provence... [whispers] et de leurs meilleurs fromages.

Strengths

What ElevenLabs v4 does best

Best at

  • Narration and voiceover that sounds performed, not read
  • Character lines with emotion and timing
  • Speech in languages other than English
  • Sound cues placed inside the speech

Trade-offs

  • It speaks in its preset voices; it does not copy a voice from a clip
  • It is priced by the length of the text, so long scripts cost more
  • Speech only: use Eleven Music for songs

Prompt guide

How to prompt ElevenLabs v4

Tips that work on this model, then example prompts to start from.

Tips

  • Write exactly what should be said; everything in the prompt is spoken except the tags.
  • Put a tag before the line it changes: [whispers], [excited], [laughs], [sighs].
  • Be specific with tags: [low, gravelly voice] works better than a vague one, which can come out as a sound effect.
  • Use ellipses and punctuation for pauses and pacing.
  • Lower stability for a more expressive read, raise it for a steady one.

Example prompts

  • A directed line

    [whispers] Did you hear that? [excited] It is them. They actually came back! [laughs] I knew it.

  • A narrator

    Every lighthouse keeps one promise... to stay lit until morning. [softly] And this one never broke it.

  • Another language

    [warmly] Bienvenidos a la cocina de mi abuela. Hoy preparamos churros... [laughs] y sí, nos vamos a comer la mitad antes de terminar.

Specs

ElevenLabs v4 specs and inputs

Made byElevenLabs, reached through Mage
OutputAudio
Image inputsNone: it generates from the prompt alone
Mentions by @handleNo
Where to use itThe Mage app, the Mage assistant, Claude and ChatGPT through the Mage MCP server, and the Mage API

Pricing

ElevenLabs v4 price and plans

Every price comes from the same pricing that bills your generations.

ModelSettingGemsPerUSDBasicProPro PlusMax
Eleven v4—30250 characters$0.03Unlimited up to 750 charactersUnlimited up to 1,500 charactersUnlimited up to 3,250 charactersUnlimited up to 4,750 characters

Prices in Gems, and in US dollars at the list price of the 10,000 Gems pack ($10). Each plan column shows what that plan runs unlimited, up to the longest length it covers; anything else costs Gems. Other settings, such as quality levels and extra input images, can change the price.

Plans and pricing

FAQ

ElevenLabs v4 questions

How much does ElevenLabs v4 cost?
Eleven v4 costs from 30 Gems (about $0.03) per 250 characters. Gems come with every paid plan and in Gem packs, you pay only for what you generate, and a generation that fails is refunded.
Can I use ElevenLabs v4 unlimited?
Yes. Eleven v4 runs unlimited from the Basic plan ($10 a month) for texts up to 750 characters. Longer texts can need a higher plan or Gems; the pricing table shows every setting.
Can I try ElevenLabs v4 for free?
Yes. New Mage accounts get 300 free Gems, enough for 10 lines of up to 250 characters with Eleven v4. No credit card is needed to start.
What can I give ElevenLabs v4 as input?
A text prompt, plus image inputs: none: it generates from the prompt alone. It takes no saved Characters or references by @handle.
Can I use ElevenLabs v4 through an API, or in Claude and ChatGPT?
Yes. The Mage API runs it as the eleven_speech model, and the Mage MCP server lets Claude, ChatGPT, and other assistants generate with it after quoting the price.
Is what I make with ElevenLabs v4 private?
Yes. Everything you generate on Mage is private by default: it appears in Explore or on your profile only if you post it.
Is this the real ElevenLabs?
Yes. Eleven Speech runs ElevenLabs' own Eleven v4 model through ElevenLabs, so the voices and the quality are the ones ElevenLabs makes. You use it with your Mage account and Gems or plan, without a separate ElevenLabs subscription.
Is ElevenLabs v4 unlimited on Mage?
Yes, on paid plans, up to a length of text each plan covers: lines up to 750 characters, about 50 seconds of speech, are unlimited from Basic, and each higher plan covers longer scripts. Longer requests run on Gems. The pricing table on this page shows the exact limits.
What are audio tags?
Words in square brackets that direct the read instead of being spoken, such as [whispers], [laughs], [sarcastic], [excited], or a sound cue like [door creaks]. Put one before the line it changes.
Which languages does ElevenLabs v4 speak?
More than 90, including Spanish, French, German, Portuguese, Japanese, Chinese, Korean, Hindi, and Arabic. Write the text in the language you want spoken; every voice can speak it.
Can it clone my voice?
Not on Mage. Eleven Speech speaks in its preset voices. To give a character a voice of its own, use Seed Audio, which takes audio references of a voice you have permission to use.
Can I use the speech commercially?
A commercial license comes with every paid Mage plan. Your audio is private by default and is shared only if you post it.

Compare

More models on Mage

  • From 3.75 Gems per second

    Seed Audio

    Voices, dialogue, music, and sound effects from one prompt, at exactly the length you ask for.

  • From 20 Gems per image

    Anima

    An anime and illustration model with clean linework, flat color, and tag-based prompting.

  • From 35 Gems per image

    Chroma

    An open-weights, general-purpose image model built on the Flux architecture.

  • From 40 Gems per image

    Flux 2

    The open-weights image model for long, detailed prompts and edits from several input images.

  • From 9 Gems per image

    GPT Image 2.5

    OpenAI's image models: prompts followed to the letter, and text in the image that actually reads.

  • From 75 Gems per image

    Grok Imagine

    xAI's Grok Imagine image model in three quality tiers, from quick ideas to polished finals.

Make your first audio with ElevenLabs v4

New accounts get 300 free Gems, enough to try Eleven v4. No install, no credit card.

Start creating for free