Eleven v4 Turbo
Top-rated natural voice in blind tests at half Eleven v4's price, fast enough for live agents. Not the cheapest.
Should you use it?
Pick it if
Developers of voice agents and apps, and narrators, who need the most natural voice with low delay.
Best for: Voice agents, apps and narration that need the most natural voice fast (Voice models Top 20)
Skip it if
You voice large volumes on a tight budget; Gemini 3.8 Flash TTS costs less than half as much per character on Artificial Analysis.
You give up: About twice the price of the 3rd and 5th ranked voices; trains on your content by default
The short version
- What this is
- ElevenLabs' fast text to speech model, the real-time version of Eleven v4. It turns text into natural speech in 90+ languages through the ElevenLabs app and API.
- Why it matters
- It is the most preferred AI voice in blind listening tests right now, at a mid-range price.
- First of 96 on the Artificial Analysis speech arena; no score yet, as its terms stop us publishing one.
- $0.04 per 1K characters now the launch promo has ended s2.
- Opt out of training in settings if your scripts are private.
Good at
Our take
Eleven v4 Turbo is the voice we would point most people to today. It ties Eleven v4 at the top of Artificial Analysis's blind listening arena s1 and costs half as much per character s2. ElevenLabs says it is available in its app, agents platform and API, and that you can start on a free account s6.
Two things to know. The launch promo ended on 12 Oct 2026, so budget at $0.04 per 1K characters s2. And ElevenLabs trains on your content unless you turn that off s4.
Score
A score from 0 to 100 per job, against everything available today.
New to this? What the scores and labels mean
- 0 to 100
- Our score for one job, like writing or coding, compared with everything else out today. 100 is the best available today. For AI models we build it from public data, such as Arena's blind votes and Epoch AI's independent tests; apps and tools are scored on our own checklist. The same tool can score differently for different jobs, and where two likely ranges overlap, we call it a tie.
- Our verdict
- Use it: a top choice for most people. Worth trying: good, and worth a go. Depends: good for some people or one kind of job. Wait: too early to tell, or not out for everyone yet. Skip: something else does the job better.
- First look
- Just released. We say what it is and whether to bother, and give it a score once public results exist.
- No score yet
- None of the public sources we use covers it yet, or the only evidence is from a source whose numbers we can't use, so we describe it in words instead.
- Best buy
- Nothing cheaper scores as well for that job.
- Best free
- The best score for that job that costs nothing, through a free plan or by running on your own computer.
- Pay as you go
- No monthly plan: you pay for each use, usually through a developer account.
- Checked
- The day we last confirmed the score and the price against the sources. Prices change often, so check the date.
- AI model
- The engine underneath, like GPT or Claude. You use it through an app or, if you code, directly.
- Open source
- Free to download and run on your own computer, so nothing leaves your machine.
Voice and audio
No score yet. The leaderboard this rests on does not let us publish numbers from it, so we describe the evidence instead.
1 source so far
Public leaderboardArtificial Analysis text to speech arena rank 1 of 96, Elo 1327, rank range 1 to 2 s1.
Alternatives
Nothing we have scored beats it for voice on score or on price.
- Eleven v4Voice model–FreeSame family, tied rank, for long expressive work; double the price. Side by side
- Gemini 3.8 Flash TTSVoice model–FreeRanks 5th at $16.50 per 1M characters on Artificial Analysis. Side by side
- Cartesia Sonic 3.6Voice modelNot reviewed yetRanks 4th, built for real-time voice.
Evidence
Everything behind the call and the scores, folded so the page stays short. Spotted a wrong price, score or link? Report a mistake.
How we scored this
Voice has no score yet, because none of the public sources we use covers it.
Public leaderboard
Reviews are drafted with help from AI models, including Anthropic's Claude. Model scores come only from outside leaderboards and independent evaluations, by a written rule.
No one paid for this review or gave us free access, and we earn nothing if you sign up. How we score
Sources 6
- s1Artificial Analysis text to speech leaderboard
- s2ElevenLabs API pricing
- s3ElevenLabs pricing
- s4ElevenLabs privacy policy
- s5ElevenLabs docs: models
- s6ElevenLabs blog: Eleven v4
Something here out of date or wrong? Report a mistake and we will check it against the source.
History 3 changes
Every change to a rating, the price or our call, with the reason. Scores are against what exists on the day, so they drift down as better things ship. Older entries come from before we moved to scores.
- Launch promo ended 12 Oct 2026; price lines now show only the list price, confirmed on the ElevenLabs API pricing page. Rating unchanged.
- New: Voice ratedReviewed: voice.
- Audit: re-opened the Artificial Analysis TTS leaderboard; rank, range, Elo and the 96-model total confirmed. Added the missing maker_disclosure field. Rating unchanged.
Use it well 4 guides on this site
Pages on this site that help with the jobs above.