Eleven v4 vs Eleven v4 Turbo
ElevenLabs released Eleven v4 and Eleven v4 Turbo together on 28 September 2026, Turbo for voice agents. Both read the same four scripts on fal on 22 October with the Sarah voice at stability 0.5 and no audio tags.
Anvisha Pai, Co-founder & CEO, Voyager
Which to use
For a finished file through fal, Turbo's saving is the price, not the wait. It costs $0.04 per thousand characters against v4's $0.08, read on 22 October 2026, and it returned each reading only a fraction of a second to a second and a half sooner: four to seven seconds against four to eight. ElevenLabs' latency figure for Turbo, about 150 ms to first speech, is measured on a stream, which this test does not use. Reading lengths were within a second of each other on every script. We have not judged either voice by ear; press play on each pair below. Use Turbo for agents and drafts, v4 where ElevenLabs' fuller model is worth twice the price to you.
Side by side, measured
| Eleven v4 | Eleven v4 Turbo | |
|---|---|---|
| Vendor | ElevenLabs | ElevenLabs |
| Released | 2026-09-28 | 2026-09-28 |
| Price | $0.08 per 1,000 characters via fal | $0.04 per 1,000 characters via fal |
| Seconds per reading | 4 to 8 | 4 to 6 |
| 4 readings cost | $0.0781 | $0.039 |
| Voices | Twenty named stock voices on fal, the same list as Eleven v3; we used Sarah, as on v3 | The same twenty named stock voices as Eleven v4 on fal; we used Sarah |
Seconds and cost are from our own runs of the same 4 scripts through each model.
The same 4 scripts, Eleven v4 against Eleven v4 Turbo
One try each, nothing re-rolled or retouched, generated by us. Eleven v4 is on the left, Eleven v4 Turbo on the right.
Ad read
14.1 against 14.0 seconds; Turbo returned in 4.1 seconds, v4 in 4.3.
›What we asked for
Meet the Ember mug. It keeps your coffee at exactly the temperature you choose, for up to ninety minutes, and it tells your phone when it's ready. Warm from the first sip to the last. Ember. Coffee, on your terms.
Explainer paragraph
26.4 seconds each; Turbo returned in 6.5 seconds, v4 in 7.8.
›What we asked for
A pour-over works in four steps. First, rinse the paper filter with hot water so it doesn't taste of paper. Second, add the grounds and pour just enough water to wet them, then wait thirty seconds while they bloom. Third, pour the rest of the water in slow circles. Fourth, wait about three minutes for it to drip through. That's it: a cup that tastes like the coffee, not the machine.
Emotional line
v4 ran 14.9 seconds, Turbo 14.2.
›What we asked for
We did it! We actually did it! I can't believe it's finally over. Okay. Okay, deep breath. Let's not tell anyone until Monday, alright? Just... let me have this one quiet night.
Names, dates and prices
Both 22.28 seconds to the hundredth, from different files.
›What we asked for
Your order ships on the 24th of September 2026 and arrives by 9:15 a.m. The total is $1,249.99, including VAT. Questions? Ask for Siobhan Nguyen or Ravi Parikh on 0800 555 0199, or email help@moda.app.
Other versions compared
Frequently asked questions
Is Eleven v4 Turbo half the price?
Yes: $0.04 against $0.08 per thousand characters on fal and on ElevenLabs' API, read on 22 October 2026.
How much faster is Turbo?
For whole files from fal, a fraction of a second to a second and a half per reading on our scripts. ElevenLabs quotes about 150 ms to first speech when streaming.
Voyager
Run any of these inside Voyager
Voyager is an agent for creative work that runs every model on this page. Brief it, and it picks the model for the job, makes the thing and hands back something you can edit. Create an account to get started.