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

Play a sample, then use the same setting for your own line.
“[whispers] I can't believe it actually worked.”
“[laughs] I can't believe it actually worked.”
“[sighs] I can't believe it actually worked.”
“[nervous][whispers] I can't believe it actually worked.”
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.
| Model | Made by | Modes | Longest text | Inputs | Test run | Test cost | Best for |
|---|---|---|---|---|---|---|---|
| Eleven v4 | ElevenLabs | Text to speech | 10,000 characters (8,000 on AdAnt) | Script with audio tags | 4 s | 0.07 credits | expressive ad reads, characters and narration |
| MiniMax Speech 2.8 | MiniMax | Text to speech | — | Script, voice description or a saved voice | 7 s | 0.08 credits | ad voiceovers, UGC and narration |
| Fish Audio Drama 3 | Fish Audio | Text to speech, multi-speaker dialogue | — | Script with bracketed directions | 3 s | 0.01 credits | short dramas, audiobooks and emotional ad reads |
| Fish Audio S2 Pro | Fish Audio | Text to speech, multi-speaker dialogue | — | Script with bracketed directions | 2 s | 0.02 credits | even, natural reads and narration |
| Eleven v4 Turbo | ElevenLabs | Text to speech | — | Script with audio tags | 2 s | 0.04 credits | drafts, 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.
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.
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.
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.
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.
$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.
[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].
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.
A UGC read with a laugh or a whisper where it sells.
Game, cartoon and drama lines with tagged reactions.
Long scripts in one consistent voice: up to 8,000 characters a run on AdAnt.
One tagged script on v3, v4 and v4 Turbo, ranked in blind listening.
The same voices at half the price, with timings measured on the same script.
Ad and UGC voiceovers from a written voice description.
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.
Running this model uses paid credits from an AdAnt plan. Creating an account is free. A short voice line costs well under 1 credit.
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.
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.
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.
VideoGoogle · fast drafts and talking clips with sound
VideoByteDance Seed · longer story clips and complex scenes with many references
VideoByteDance Seed · UGC ads and product clips with references
VideoByteDance Seed · testing many hooks and ideas cheaply
VideoTopview · longer single takes and calm, natural clips
MotionKuaishou (Kling AI) · putting a consistent character into a proven performance
ImageGoogle DeepMind · photoreal product shots and keeping a product on brand
ImageGoogle DeepMind · fast social images, thumbnails and drafts
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