Eleven v4 vs Eleven v3
Eleven v4 is the model ElevenLabs released on 28 September 2026, six months after Eleven v3 reached general availability. Both read the same four scripts on fal with the Sarah voice at stability 0.5 and no audio tags: v3 on 10 September, v4 on 22 October.
Anvisha Pai, Co-founder & CEO, Voyager
Which to use
Switch to v4 for new work, unless a pipeline is tuned to v3's delivery. On fal v4 costs $0.08 per thousand characters against v3's $0.10, read on 22 October and 10 September 2026, and it returned every reading sooner: four to eight seconds against seven to ten. ElevenLabs' own API now charges $0.08 for both. ElevenLabs says v4 is more emotive and follows tags and pronunciation more closely. We have not judged either voice by ear; press play on each pair below. The readings differ in pace: v4 took two seconds longer over the narration paragraph and two seconds less over the names and numbers. One reading per script is a first look, not a ranking.
Side by side, measured
| Eleven v4 | Eleven v3 | |
|---|---|---|
| Vendor | ElevenLabs | ElevenLabs |
| Released | 2026-09-28 | 2026-03-14 |
| Price | $0.08 per 1,000 characters via fal | $0.10 per 1,000 characters via fal |
| Seconds per reading | 4 to 8 | 7 to 10 |
| 4 readings cost | $0.0781 | $0.0976 |
| Voices | Twenty named stock voices on fal, the same list as Eleven v3; we used Sarah, as on v3 | Twenty named stock voices on fal, from Aria to Bill; 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 v3
One try each, nothing re-rolled or retouched, generated by us. Eleven v4 is on the left, Eleven v3 on the right.
Ad read
14.1 seconds from v4 against 13.8 from v3.
›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
v4 read the paragraph in 26.4 seconds, the longest on the site; v3 took 24.5.
›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
14.9 seconds from v4, 13.0 from v3. Neither had audio tags, so both performed from the words alone.
›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
v4 was quicker here: 22.3 seconds against 24.7.
›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 cheaper than Eleven v3?
On fal, yes: $0.08 against $0.10 per thousand characters. On ElevenLabs' own API both are $0.08, read on 22 October 2026.
Is Eleven v4 faster?
On our four scripts through fal, v4 returned in four to eight seconds and v3 in seven to ten. For real-time use ElevenLabs points to Eleven v4 Turbo.
Were both run the same way?
Same scripts, same Sarah voice, stability 0.5, no audio tags, one attempt each, through fal. v3 ran on 10 September and v4 on 22 October 2026.
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.