50% off yearly plansLimited time — ends in 50% off yearly plans · ends in

Eleven v4 AdAnt · by ElevenLabs

ElevenLabs Eleven v4 AI Voice Generator

Eleven v4 is the voice model ElevenLabs calls its most expressive: put tags like [whispers] or [laughs] in the script and it performs them.

  • Audio tags
  • Up to 10,000 characters (ElevenLabs)
  • $0.08 per 1k characters
Made with Eleven v4“[whispers] Okay, don't tell anyone. [laughs] I finally found a serum that actually works. [sighs] It only took me three years.” · Eleven v4, ElevenLabs voice Jessica, one take

  • [whispers]

    “[whispers] I can't believe it actually worked.”

  • [laughs]

    “[laughs] I can't believe it actually worked.”

  • [sighs]

    “[sighs] I can't believe it actually worked.”

  • [nervous][whispers]

    “[nervous][whispers] I can't believe it actually worked.”

Same script, every voice model: a UGC voiceover

We ran this script once on each model, with no retries and no edits: a warm, friendly woman in her late twenties, casual like a creator talking to a friend: described on MiniMax, and the preset voices Sarah on Fish Audio and Jessica on ElevenLabs. Whether it sounds like a person talking rather than reading, and where it pauses.

Okay, real talk. I've tried every serum on my feed, and this is the only one I've ever finished twice. Two drops, every morning. My skin just looks awake now.
Eleven v4Ready in 4 s · 0.07 credits
MiniMax Speech 2.8Ready in 7 s · 0.08 credits
Fish Audio Drama 3Ready in 3 s · 0.01 credits
Fish Audio S2 ProReady in 2 s · 0.02 credits
Eleven v4 TurboReady in 2 s · 0.04 credits

Voice models compared

ModelMade byModesLongest textInputsTest runTest costBest for
Eleven v4ElevenLabsText to speech10,000 characters (8,000 on AdAnt)Script with audio tags4 s0.07 creditsexpressive ad reads, characters and narration
MiniMax Speech 2.8MiniMaxText to speech—Script, voice description or a saved voice7 s0.08 creditsad voiceovers, UGC and narration
Fish Audio Drama 3Fish AudioText to speech, multi-speaker dialogue—Script with bracketed directions3 s0.01 creditsshort dramas, audiobooks and emotional ad reads
Fish Audio S2 ProFish AudioText to speech, multi-speaker dialogue—Script with bracketed directions2 s0.02 creditseven, natural reads and narration
Eleven v4 TurboElevenLabsText to speech—Script with audio tags2 s0.04 creditsdrafts, long scripts and fast turnaround

Test run and cost come from the same-script run above: the seconds until the finished file came back, and the credits for its characters. Longer scripts cost more; the try-it panel shows the price before you run.

Eleven v4 key features

Audio tags it follows

Write [whispers], [laughs] or [sighs] where it should happen. ElevenLabs says v4 handles tags better than its earlier models, and you can combine them, as in [whispering, playful]. In our run, [nervous][whispers] worked too.

Eleven v4 vs v3

ElevenLabs allows 10,000 characters per v4 request (v3: 5,000) and says v4 follows tags more closely. Like v3, v4 does not support SSML such as <break>; use punctuation or a tag for pauses.

Pronunciation you can fix

ElevenLabs says v4 reads IPA written between slashes, so you can spell a hard name the way it should sound, which helps with brand names and made-up words.

Voice cloning is on ElevenLabs, not AdAnt

ElevenLabs' own app clones voices for v4 (Instant and Professional Voice Clones). AdAnt does not clone voices: it runs v4 with ElevenLabs' preset voices, like Jessica in these samples.

Pricing

$0.08 per 1,000 characters on OpenRouter (as of November 2026). Our 11-second ad read cost 0.07 AdAnt credits; v4 Turbo is half the price.

  1. Type a line, or keep the example.
  2. Pick an audio tag, or play the samples first.
  3. Press Create. The read plays here in a few seconds.

How to write an Eleven v4 script with audio tags

[tag for the opening mood, e.g. whispers] First sentence. [a reaction, e.g. laughs] Second sentence. [a change, e.g. sighs] Last sentence. Stack tags for a mix: [nervous][whispers].

ElevenLabs Eleven v4: Try the Audio Tags Online

Eleven v4 is ElevenLabs' text-to-speech model, released on September 28, 2026 together with a faster v4 Turbo. ElevenLabs allows up to 10,000 characters per request, and it performs audio tags such as [whispers] and [laughs] written into the script. AdAnt runs it with ElevenLabs' preset voices, so you can try it here without an ElevenLabs account.

Ad voiceovers

A UGC read with a laugh or a whisper where it sells.

Characters

Game, cartoon and drama lines with tagged reactions.

Long narration

Long scripts in one consistent voice: up to 8,000 characters a run on AdAnt.

Eleven v4 vs v3

One tagged script on v3, v4 and v4 Turbo, ranked in blind listening.

Eleven v4 Turbo

The same voices at half the price, with timings measured on the same script.

ElevenLabs Eleven v4 AI Voice Generator FAQ

Tips for a better result
  • Put a tag right before the words it should change.
  • Use punctuation and tags for pauses; v4 does not support SSML <break>.
  • Write numbers and brand names the way they are said.
How much does Eleven v4 cost?

On OpenRouter Eleven v4 lists at $0.08 per 1,000 characters, and v4 Turbo at $0.04 (as of November 2026). On AdAnt our 11-second ad read used 0.07 credits; ElevenLabs' own plans price it in their own credits.

Is Eleven v4 free?

Running this model uses paid credits from an AdAnt plan. Creating an account is free. A short voice line costs well under 1 credit.

Is there an Eleven v4 API?

Yes: ElevenLabs' own API, OpenRouter as elevenlabs/eleven-v4, or AdAnt's media API or the command adant-cli media audio generate --model eleven-v4, paid in AdAnt credits with no ElevenLabs key.

Can Eleven v4 clone my voice?

On ElevenLabs, yes: ElevenLabs says v4 supports Instant Voice Clones, from a short sample (it suggests one to two minutes of audio), and Professional Voice Clones (as of November 2026). AdAnt does not clone voices: it runs Eleven v4 with ElevenLabs' preset voices only.

Eleven v4 vs v3: what changed?

ElevenLabs says v4 follows audio tags more reliably than v3, and it allows 10,000 characters per request against v3's 5,000 (as of November 2026). Neither supports SSML <break>. In our blind test of one tagged script, v3 came last.

Use Eleven v4 for

Eleven v4 compared by use case

Try another model

Compare every model

Want the whole ad, not just the voice?

AdAnt's agents research your market, write the script, pick the right model for each shot and make the video in one chat.

Start with AdAnt