Faster than v4
On the same 11-second script, Turbo's file came back in 2.2 seconds against 4.1 for v4. On the shorter tagged line above, the two were within 0.2 seconds of each other.
Eleven v4 Turbo AdAnt · by ElevenLabs
Eleven v4 Turbo is the low-latency version of ElevenLabs' v4: the same voices and audio tags, at half the price.

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 Turbo | ElevenLabs | Text to speech | — | Script with audio tags | 2 s | 0.04 credits | drafts, long scripts and fast turnaround |
| 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 | 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 |
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.
On the same 11-second script, Turbo's file came back in 2.2 seconds against 4.1 for v4. On the shorter tagged line above, the two were within 0.2 seconds of each other.
$0.04 per 1,000 characters on OpenRouter, against $0.08 for v4 (as of November 2026). Our test read cost 0.04 credits.
Turbo takes the same audio tags and ElevenLabs voices as v4. In our runs it whispered, laughed and sighed where the tags said.
[mood tag, e.g. whispers] Hook sentence. [reaction tag, e.g. laughs] The point. [closing tag, e.g. sighs] The payoff.
Eleven v4 Turbo is the low-latency version of ElevenLabs' Eleven v4, released with it on September 28, 2026. It uses the same voices and audio tags at half v4's price. AdAnt runs it with ElevenLabs' preset voices, so you can try it here without an ElevenLabs account.
Hear a script before you pay for the final read.
Narration and explainers where half the price adds up.
Ten hook versions of one ad for the price of five.
The full v4 model: audio tag samples, pricing, API and voice cloning.
In our runs the two sounded close on a plain ad read. Turbo costs half as much and returned our 11-second read in 2.2 seconds against 4.1, so use it for drafts and volume, and v4 when a take needs the most nuance.
Running this model uses paid credits from an AdAnt plan. Creating an account is free. A short voice line costs well under 1 credit.
Our 11-second read came back complete in 2.2 seconds through OpenRouter, the route AdAnt uses. ElevenLabs built Turbo for low latency.
$0.04 per 1,000 characters on OpenRouter (as of November 2026). On AdAnt our 11-second ad read used 0.04 credits.
Yes: ElevenLabs' own API, OpenRouter as elevenlabs/eleven-v4-turbo, or AdAnt's media API or the command adant-cli media audio generate --model eleven-v4-turbo, paid in AdAnt credits with no ElevenLabs key.
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