Eleven v4
Eleven v4 is ElevenLabs' text-to-speech model released on 28 September 2026, which the company calls its most emotive yet, on a new architecture. It keeps Eleven v3's square-bracket audio tags, adds natural-language delivery instructions and better IPA pronunciation, supports more than 90 languages, and ElevenLabs says its instant voice clones work from about ten seconds of audio. A faster sibling, Eleven v4 Turbo, is aimed at voice agents. On fal and on ElevenLabs' API it costs $0.08 per thousand characters.
Anvisha Pai, Co-founder & CEO, Voyager
ElevenLabs · released
›What we asked for
Hi, I'm Eleven v4, the newest voice model from ElevenLabs. I read scripts in more than ninety languages, and if you write a stage direction in square brackets, I'll try to act it. Here is the same script every voice on this site reads, so you can compare us.
elevenlabs/tts/eleven-v4
voice: Sarah, stability: 0.5
returned 16.1 seconds of mp3
At a glance
- Price
- $0.08 per thousand characters on fal and on ElevenLabs' API; our four scripts cost about eight cents.
- Voices
- Twenty named stock voices on fal, the same list as Eleven v3; we used Sarah, as on v3. Cloning is on ElevenLabs' own platform.
- Audio tags
- Square-bracket directions like [whispers] plus plain-language instructions; our scripts used neither.
- Languages
- More than 90, per ElevenLabs.
- Turbo sibling
- Eleven v4 Turbo is half the price and built for real-time agents.
Other ElevenLabs models: Eleven v4 Turbo, Eleven v3. Compare all 3.
Anvisha's take
We have not scored the four readings by ear; press play and judge the voice yourself. What we measured: Eleven v4 read the four scripts in 14 to 26 seconds of audio each, returning in four to eight seconds, quicker than Eleven v3's seven to ten, for eight cents across all four, against v3's ten. It ran with the same Sarah voice and stability of 0.5 we gave v3, so the two pages compare like for like. It read the narration paragraph in 26.4 seconds, the longest reading of it on the site, two seconds slower than v3; it read the names-and-numbers script in 22.3, two seconds quicker. No audio tags were sent, so the emotion script is what v4 does from the words alone.
Eleven v4 real output: the same 4 scripts every model gets
Every voice model on this site gets the same 4 scripts, so you can compare like with like. These are the readings Eleven v4 returned, one try each, nothing re-rolled or retouched. Generated on . The 4 readings took 4 to 8 seconds each and cost $0.0781 in total.
Pacing, warmth and whether the pauses land where a voice actor would put them.
›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.
elevenlabs/tts/eleven-v4
voice: Sarah, stability: 0.5
returned 14.1 seconds of mp3
Steady narration over a long paragraph, clean list rhythm and a natural close.
›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.
elevenlabs/tts/eleven-v4
voice: Sarah, stability: 0.5
returned 26.4 seconds of mp3
Range: excitement, then a hushed aside, from the words alone with no tags.
›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.
elevenlabs/tts/eleven-v4
voice: Sarah, stability: 0.5
returned 14.9 seconds of mp3
Reading numbers, times, currency, an email address and two hard names correctly.
›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.
elevenlabs/tts/eleven-v4
voice: Sarah, stability: 0.5
returned 22.3 seconds of mp3
How the cost under each picture was worked out: fal's Eleven v4 rate of $0.08 per 1,000 characters (fal model page and pricing API, read 2026-10-22) for the 213 characters sent; fal does not return the charge.
Compare Eleven v4
Eleven v4 pricing
| Where | Unit | Price | Source |
|---|---|---|---|
| fal | 1,000 characters | $0.08 | fal model page and pricing API, read |
| ElevenLabs API | 1,000 characters Eleven v3 and Multilingual v2 are also $0.08 there now; v4 Turbo is $0.04. | $0.08 | ElevenLabs API pricing, read |
Is Eleven v4 free?
ElevenLabs' free plan gives 10,000 credits a month, and the v4 announcement invites free accounts to generate with v4. The free plan's feature list has no commercial licence; Starter, at $6 a month for 30,000 credits, does. fal charges per character with no free tier.
- •Free: 10,000 credits a month, no commercial licence listed.
- •Starter $6 a month: 30,000 credits and a commercial licence.
- •fal: $0.08 per thousand characters, no free tier.
ElevenLabs pricing, read
Where to use Eleven v4
- ElevenLabs · Free plan and paid tiers; voice cloning, dubbing and agents.
- ElevenLabs API · Model id eleven_v4 in ElevenLabs' sample code; up to 10,000 characters a request there.
- fal · $0.08 per thousand characters, stock voices, up to 5,000 characters a request.
- Voyager · Runs inside Voyager, the agent for creative work, on Voyager credits on every paid plan (about 7.2 credits a minute of speech), or with your own fal key.
Voyager
Run Eleven v4 inside Voyager
Voyager is an agent for creative work that runs every model in this reference, Eleven v4 included. Brief it, and it picks the model, makes the thing and hands back something you can edit. Create an account to get started.
What we noticed running Eleven v4
- •26.4 seconds for the paragraph, the longest reading of it on the site; Eleven v3 took 24.5 and Kokoro 22.9 on the same 385 characters. See the explainer paragraph reading.
- •22.3 seconds, two seconds shorter than Eleven v3 on the same script, and to the hundredth the same length as v4 Turbo's, though the two files differ. See the names, dates and prices reading.
- •Returned in four to eight seconds per reading, faster than Eleven v3's seven to ten and barely slower than v4 Turbo's four to seven.
- •No audio tags were sent, so the excitement and the hushed aside come from the words alone, as on every voice page here. See the emotional line reading.
Eleven v4 limits and API parameters
| Limit | Value |
|---|---|
| Script length on fal | 5,000 characters a request; ElevenLabs' own API takes up to 10,000. fal API reference, read |
| SSML | The <break> tag is disabled in v4; ElevenLabs points to tags such as [pause] instead. |
| Voices on fal | Stock voices only; no cloning through fal. fal API reference, read |
›Every setting, for developers
fal (elevenlabs/tts/eleven-v4)
fal API reference, read
| Parameter | Type | Values | Default |
|---|---|---|---|
| text | string | The script, up to 5,000 characters, with optional [audio tags] and IPA in forward slashes Required. | |
| voice | string | Aria, Roger, Sarah, Laura, Charlie, George, Callum, River, Liam, Charlotte, Alice, Matilda, Will, Jessica, Eric, Chris, Brian, Daniel, Lily, Bill fal's listed default is not among its listed examples. | Rachel |
| stability | number | 0 to 1 Lower is more expressive, higher more consistent. | 0.5 |
| similarity_boost | number | 0 to 1 | 0.75 |
| language_code | string | ISO 639-1 code | |
| apply_text_normalization | enum | auto, on, off Spells out numbers and dates before reading. | auto |
| seed | integer | 0 to 4294967295 Best effort; identical output is not guaranteed. | |
| timestamps | boolean | true, false | false |
| output_format | enum | mp3, PCM, Opus, mu-law and A-law at several rates | mp3_44100_128 |
What Eleven v4 will not say
ElevenLabs' terms put all use under its Prohibited Use Policy, and a voice model must be your own voice or one you are authorised to share. The free plan's feature list carries no commercial licence; Starter at $6 a month does.
Alternatives to Eleven v4
Frequently asked questions
What is Eleven v4?
ElevenLabs' text-to-speech model released on 28 September 2026, which ElevenLabs calls its most emotive, with audio tags, natural-language delivery instructions and more than 90 languages.
How much does Eleven v4 cost?
$0.08 per thousand characters on fal and on ElevenLabs' API, read on 22 October 2026. Eleven v4 Turbo is $0.04.
Is Eleven v4 better than Eleven v3?
We have not judged the voices by ear. On our four scripts v4 returned faster, four to eight seconds against seven to ten, and cost a fifth less on fal, $0.08 against $0.10 per thousand characters.
Is Eleven v4 free?
ElevenLabs' free plan gives 10,000 credits a month and its announcement invites free accounts to try v4. Commercial use starts at the $6 Starter plan.
How this page is made
Prices, limits and settings are read from the linked vendor and host pages on the dates shown. Every picture was generated by us through fal with the request shown under it, and the original files are kept unedited. A generation that failed is shown as a failure. Model and vendor names are used to identify the products; no vendor imagery appears on this page.
