Sign up and save up to 50% on a yearly plan.Sign up free →Black Friday: up to 50% off yearly plans.See the deal →

Direct the delivery, not just the words.

ElevenLabs v3 AI voice generator

Write a script, pick one of 20 ElevenLabs voices and steer the read with audio tags like [whispers], [sighs] or [laughs]. A finished MP3 voiceover in seconds.

From $0.068 per 1,000 characters on MAX yearly

  • 70+ languages
  • 20 voices
  • Up to 5,000 characters a read

● Made with ElevenLabs v3

Hear ElevenLabs v3

Every sample is one read, with the script that made it and what it cost.

  • “Your morning, sorted. Fresh coffee beans, roasted on Monday and at your door by Wednesday. First bag is on us, so you only pay for the ones you love.”

    Sarah
    149 characters · 3 credits
  • “[whispers] Okay, I have to tell you something. [laughs] I actually finished the whole marathon. [sighs] My legs, however, have not forgiven me.”

    Laura · audio tags
    143 characters · 3 credits
  • “In 1924, a small workshop on the edge of town built its first wooden chair. A hundred years later, the same family still sands every joint by hand. This is their story.”

    George
    168 characters · 3 credits
  • “Stop scrolling. If your skin feels tight by lunchtime, it is not your fault. It is your cleanser. Here is the two-minute swap that fixed mine.”

    Charlotte
    142 characters · 3 credits

● Why people pick it

What is ElevenLabs v3 good at?

01

Audio tags

Square-bracket tags in the script set emotion, delivery and reactions: [whispers], [shouts], [laughs], [sighs].

02

Wide emotional range

ElevenLabs built v3 for dramatic delivery: restrained narration and big character moments from the same voice.

03

70+ languages

The same voice reads in more than seventy languages. Set the language code when the script needs it.

04

Fine control

Stability, similarity, style and speed sliders shape the read when a tag is not enough.

● Use cases

What people make with ElevenLabs v3

Character voiceovers

Give an animated mascot or a game character a voice that laughs, sighs and whispers on cue.

Audiobook and story narration

ElevenLabs recommends v3 for audiobook narration and emotional dialogue: long reads with real changes in tone.

Ad reads with a reaction

A hook that gasps, a punchline that laughs. Tags put the moment where the script needs it.

● Side by side

How does ElevenLabs v3 compare?

The other voice models on OpenClips, on the same credits.

SpecElevenLabs v3ElevenLabs v4ElevenLabs v4 TurboMiniMax Speech 2.8 Turbo
Made byElevenLabs v3ElevenLabsElevenLabs v4ElevenLabsElevenLabs v4 TurboElevenLabsMiniMax Speech 2.8 TurboMiniMax
Price per 1,000 charactersElevenLabs v316.3 creditsElevenLabs v416.3 creditsElevenLabs v4 Turbo8.2 creditsMiniMax Speech 2.8 Turbo12.3 credits
A 1,000-character readElevenLabs v317 creditsElevenLabs v417 creditsElevenLabs v4 Turbo9 creditsMiniMax Speech 2.8 Turbo13 credits
Longest scriptElevenLabs v35,000 charactersElevenLabs v410,000 charactersElevenLabs v4 Turbo10,000 charactersMiniMax Speech 2.8 Turbo5,000 characters
VoicesElevenLabs v320ElevenLabs v420ElevenLabs v4 Turbo20MiniMax Speech 2.8 TurboBy voice id
OutputElevenLabs v3MP3ElevenLabs v4RASTERElevenLabs v4 TurboRASTERMiniMax Speech 2.8 TurboRASTER

Prices are the catalog's, quoted before every render.

● Specs

ElevenLabs v3 specs

StatusLive in the app, the API and the MCP
Made byElevenLabs
ModalityText to speech
InputsText script
Longest script5,000 characters
Voices20: Aria · Roger · Sarah · Laura · Charlie · George · Callum · River · Liam · Charlotte · Alice · Matilda · Will · Jessica · Eric · Chris · Brian · Daniel · Lily · Bill
Languages70+ languages
Languagemixed · af · ar · hy · as · ast · az · be · bn · bs · bg · my · yue · ca · ceb · ny · hr · cs · da · nl · en · et · fil · fi · fr · gl · ka · de · el · gu · ha · he · hi · hu · is · id · ga · it · ja · jv · kn · kk · ko · ky · lv · ln · lt · lb · mk · ms · ml · mt · zh · mi · mr · mn · ne · no · oc · or · ps · fa · pl · pt · pa · ro · ru · sr · sd · sk · sl · so · es · sw · sv · tg · ta · te · th · tr · uk · ur · uz · vi · cy · yo
Output formatMP3 22.05 kHz 32 kbps · MP3 44.1 kHz 32 kbps · MP3 44.1 kHz 64 kbps · MP3 44.1 kHz 96 kbps · MP3 44.1 kHz 128 kbps · MP3 44.1 kHz 192 kbps
Similarity boost0–1
Speed0.7–1.2
Stability0–1
Style0–1
Audio tagsEmotions [sad] [happily], delivery [whispers] [shouts], reactions [laughs] [sighs]
SSMLNot supported: pauses come from tags and punctuation
OutputMP3 audio
Price16.3 credits per 1,000 characters · $0.068 per 1,000 characters on MAX yearly
A 1,000-character read17 credits

● How it works

How do you use ElevenLabs v3 on OpenClips?

01

Describe it

Write the script, up to 5,000 characters. Every word is read aloud.

02

Pick a voice

20 voices. Play a sample, then keep the one that fits the script.

03

Pick the settings and generate

Choose the settings ElevenLabs v3 offers, then generate. The result lands in your library.

● Tips

Tips for better results with ElevenLabs v3

  • Tag the moment, not the line

    Put a tag right before the words it should change: "[whispers] Don't tell anyone." One or two tags per sentence read best.

  • Punctuation is your pause

    v3 ignores SSML break tags. Commas, full stops and ellipses set the rhythm instead.

  • Keep it under 5,000 characters

    That is about five minutes of speech. Split a longer script into chapters and read each one.

  • Try v4 for the final

    ElevenLabs calls v4 a net upgrade over v3 in almost every case, with the same tags. Some voices still sound the way you want on v3, so compare both.

● Made for

What can you make with ElevenLabs v3?

Video voiceoversAudiobooksGame charactersAnimated explainersPodcast introsAd hooksStory reelsMultilingual dubs

● Questions

ElevenLabs v3 FAQ

ElevenLabs v3 is a text-to-speech model by ElevenLabs. ElevenLabs' expressive speech model, with audio tags for emotion and delivery.

Short words in square brackets inside the script, like [whispers], [laughs], [sighs] or [sad]. The voice performs them instead of reading them aloud, so you direct the delivery from the text.

ElevenLabs calls v4 its newest and highest-quality model, with 90+ languages and a 10,000-character limit, and v3 the previous generation. The same audio tags work on both. v3 adds style and speed sliders that v4 does not have.

No. ElevenLabs says v3 and v4 do not support SSML break tags. Use audio tags and punctuation to shape pauses and pacing.

ElevenLabs v3 opens with your first purchase: any plan or credit pack. A new account still gets ⚡30 on signup with no card, for the models the free plan runs.

ElevenLabs v3 costs 16.3 credits per 1,000 characters, paid from your OpenClips credits. That is from $0.068 per 1,000 characters on MAX yearly. A 1,000-character script costs 17 credits. The charge is the characters you send, rounded up once.

Up to 5,000 characters a read. A longer script is refused before any credit is held, so split a long script into reads.

20 voices: Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill. Pick one per read.

70+ languages, as ElevenLabs documents it.

An MP3 file, saved to your library, ready to download or to drop on a video.

Per 1,000 characters: ElevenLabs v3 17 credits, ElevenLabs v4 17 credits, ElevenLabs v4 Turbo 9 credits, MiniMax Speech 2.8 Turbo 13 credits. The table above sets their scripts, voices and files side by side.

Yes. ElevenLabs v3 runs from the OpenClips app, the REST API and the MCP server, with the same settings and the same price.

● The receipts

Where do these ElevenLabs v3 facts come from?

Every link goes to the vendor's own page.

Give your script a voice

20 voices, audio tags, 70+ languages.

Generate with ElevenLabs v3

What ElevenLabs v3 does

ElevenLabs v3 turns a written script into speech with real emotional range. ElevenLabs describes it as its emotionally rich, expressive model, built for dramatic delivery. On OpenClips you pick one of 20 voices, write up to 5,000 characters, and get an MP3 back in your library.

Audio tags, explained

A tag is a word in square brackets: [whispers], [shouts], [laughs], [sighs], [sad], [happily]. The voice acts it out at that point in the script. Tags are how v3 does what SSML used to: ElevenLabs v3 does not read SSML break tags, so pauses come from tags and punctuation.

ElevenLabs v3 vs v4

ElevenLabs v4 is the newer model: 90+ languages, scripts up to 10,000 characters, and better voice accuracy by ElevenLabs' own account. v3 keeps the style and speed sliders v4 dropped, and some voices simply sound the way you want on v3. ElevenLabs v4 Turbo is the real-time sibling, at about half the price per character.