ElevenLabs v3 Text to Speech

Direct ElevenLabs v3 with audio tags like [whispers], [sighs] and [laughs] and turn your script into an acted, emotional voiceover in 70+ languages.

Turn Written Scripts into Acted Performances with ElevenLabs v3

Last verified: November 3, 2026

Type [whispers], [sighs] or [laughs] into your script, and ElevenLabs v3 acts out each cue at the spot where you put it. You get back a performed voice take, not a flat read. ElevenLabs built the model, officially named Eleven v3, as its emotionally rich, expressive text-to-speech engine . It first came out as an alpha in June 2025 and became generally available on February 2, 2026 .

Its audio tags come in three groups. Emotion tags include [sad], [angry] and [happily]. Delivery tags include [whispers] and [shouts]. Reaction tags include [laughs], [clears throat] and [sighs]. The model also has deeper text understanding, so it gets better stress, cadence and expressivity from the words themselves . It produces lifelike speech with a wide emotional range in more than 70 languages .

Expect to direct it, not just paste text in. ElevenLabs says the model needs more prompt engineering than its earlier models , and it rewards scripts with clear emotional context. On this page it runs as ElevenLabs V3 in text-to-speech mode and makes one finished take from each script.

What One Text-to-Speech Run Handles

What one run accepts and returns, plus how much audio a full script makes.

Script length per run

Up to 5,000 characters

Audio from a full-length script

About 5 minutes

Preset voices

26, with Rachel as default

Stability modes

Creative, Natural (default), Robust

Spoken language

Auto-detect or 71 named languages

Output per run

1 audio file

Check These Before You Generate a Take

Six checks that stop a flat delivery, ignored cues or a misread script.

1

Pick the Voice Before You Write Tags

The voice you choose matters more than any other setting in Eleven v3 . Pick a preset whose natural tone already suits the scene. A soft-spoken voice is a poor match for a script built around [shouts].

2

Set Stability for How Much You Direct

Robust makes the model less responsive to directions in the text . Use Natural or Creative for scripts with lots of tags. Save Robust for plain reads where consistency matters more than performance.

3

Put Each Tag Right Before Its Words

Place a tag just before the phrase it should shape. Use one or two at each turn in the scene instead of tagging every sentence. Opposing cues side by side, like [happily] next to [sad], give the performance no clear direction.

4

Shape Pauses with Punctuation, Not SSML

Eleven v3 doesn't support SSML break tags, and the structure of your text strongly affects the result . Use ellipses, dashes and capital letters to set rhythm and emphasis.

5

Choose a Language for Short or Mixed Text

Auto works out the language from your text. If your script is one short line or mixes languages, pick the spoken language yourself so Auto doesn't have to guess.

6

Read Enhance Prompt Suggestions Before Accepting

Enhance Prompt expands a rough idea, and every word of a suggestion you pick will be spoken. Your text only changes when you pick one, so check that it keeps your tags and any lines that must stay exactly as written.

Pick Your Voice Engine

ElevenLabs v3 or MiniMax Speech: Choose the Engine That Fits Your Script

Both engines let you write performance cues into the script itself. They differ in how many languages they cover, how much text one request takes and how they handle hard-to-read text. Each row compares what the two models do as ElevenLabs and MiniMax document them. Where a MiniMax fact applies to one release, that release is named.

Feature/Spec ElevenLabs v3 MiniMax Speech
Release milestones Alpha released June 2025 ; generally available February 2, 2026 Speech-02 series released April 2, 2025; Speech-2.8 released January 23, 2026
Language coverage 70+ languages 40 languages on speech-2.8-hd
Text accepted in one request 5,000 characters, roughly 5 minutes of audio Up to 10,000 characters per synchronous request
Emotion direction Inline emotion tags such as [sad], [angry], [happily], plus delivery tags such as [whispers] and [shouts] 7 supported emotions on speech-2.8-hd
Non-verbal sounds written into the script Reactions in square brackets such as [laughs], [clears throat], [sighs] Interjection tags in parentheses such as (sighs), on speech-2.8-hd and speech-2.8-turbo only
Pronunciation override Native International Phonetic Alphabet (IPA) support Inline IPA, Mandarin Pinyin or Cantonese Jyutping in half-width parentheses
Numbers, symbols and formatted text 68% fewer errors on numbers, symbols and notation since leaving alpha Speech 2.6 reads URLs, email addresses, phone numbers, dates and money amounts without text pre-processing

What the Differences Mean for Your Next Voiceover

Writing performance cues into the script

Both engines take cues inside the text, so a script can carry its own stage directions. Eleven v3 uses square brackets for everything: feelings, delivery and reactions. A tagged script reads like a director's draft. MiniMax splits the job between its documented set of emotions and parenthesized sound interjections, and the interjections only work on the speech-2.8 models. If you move a script from one engine to the other, plan to rewrite the cues, because the two syntaxes don't match.

Planning around language reach and script length

Here the two engines pull in opposite directions. Eleven v3 covers far more languages, which matters when one voiceover has to ship in many markets. MiniMax's synchronous requests take twice as much text, so long documents need fewer splits. On this page, the Text box has the same 5,000-character ceiling as Eleven v3 itself. Plan a long chapter as several runs from the start.

Handling names, numbers and formatted text

Both models accept IPA for pinning down a hard name. MiniMax also documents Pinyin and Jyutping for Chinese. Their work on formatted text targets different material. Eleven v3's general release focused on numbers, symbols and notation in every language, like scores, formulas and digit-by-digit phone numbers. Speech 2.6 focused on the URLs, emails and dates that turn up in agent replies. Look at what your scripts are full of and test that kind of text first.

Choose by Language Reach or by Text per Request

How to choose: Choose ElevenLabs v3 when one engine has to cover many languages: it supports 70+, against 40 on MiniMax speech-2.8-hd. Choose MiniMax Speech when one request has to hold more text: its synchronous requests take up to 10,000 characters, against 5,000 for Eleven v3. For non-verbal sounds written into the script and IPA pronunciation, the two are equal. Eleven v3 and the MiniMax speech-2.8 models both support them.

Generate a Directed Voice Take

Four steps take you from a tagged script to a finished audio take.

1

Write Your Script in the Text Box

Type or paste your script into Text. It holds up to 5,000 characters. Add audio tags such as [whispers] or [laughs] right before the words they should shape. If you only have a rough idea, Enhance Prompt under the box suggests fuller versions.
2

Choose a Voice

Open Voice and pick one of the 26 presets. Rachel is selected by default. Choose the one whose natural tone is closest to the performance you want.
3

Set Stability and Language

Leave Stability on Natural, or switch to Creative for more expressive reads or Robust for the steadiest delivery. Leave Language on Auto to detect it from your text, or pick one of the 71 named languages.
4

Click Generate

Press Generate to make one audio file from your script. If a moment doesn't land, change a tag, the punctuation or Stability, and generate again for a new take.

Frequently Asked Questions

What is ElevenLabs v3 best used for?

It's best for scripts that need acting rather than reading. You write emotion, delivery and reaction cues such as [angry], [whispers] or [clears throat] into the text, and the model performs them, with a wide emotional range in more than 70 languages . ElevenLabs says it works well for character conversations, audiobook narration and emotional dialogue. On this page, you type those cues straight into the Text box.

What changed when ElevenLabs v3 came out of alpha?

The generally available release, announced February 2, 2026, is more stable. In ElevenLabs' testing, users preferred it over the alpha 72% of the time . It also reads numbers, symbols and specialized notation more accurately in every language. For example, it reads a phone number digit by digit instead of as one huge figure. That matters most for scripts full of scores, prices, formulas or codes.

Can ElevenLabs v3 power a real-time voice agent?

ElevenLabs uses a separate model, Eleven v3 Conversational, for real-time speech, with latency around 165 ms . The generator on this page runs ElevenLabs V3 text to speech and returns one finished audio file per run. That fits pre-produced voiceovers, narration and character lines, not live back-and-forth conversation.

How do I voice a script longer than 5,000 characters?

Split it into parts that each fit in the Text box. Cut at scene or paragraph breaks so every take starts and ends on a complete thought. Use the same Voice, Stability and Language for every part, then join the files in your audio editor. Each run is a new performance, so listen across the joins and regenerate any part whose energy doesn't match the one before it.

How is Eleven v4 different from ElevenLabs v3?

Eleven v4 came out after v3, and ElevenLabs now lists Eleven v3 as its previous-generation speech model . ElevenLabs says v4 improves output quality, voice accuracy, emotion, audio tags and language coverage compared with v3 . The generator on this page runs ElevenLabs V3, so you work with v3's audio tags, its three Stability modes and the 5,000-character Text box.

How is the cost of an ElevenLabs v3 run shown?

On Vidofy, every visitor can see in the model list the credits an ElevenLabs V3 run starts from. Once you're signed in, the cost of the options you chose appears above the Generate button. For this version, it changes with the length of the text in the Text box. Enhance Prompt suggestions don't use credits.