JetBrains' open 12B mixture-of-experts coding model with 2.5B parameters active per token under Apache 2.0
Eleven v4 Turbo
New· 4Low-latency version of ElevenLabs' Eleven v4 speech model, aimed at phone and chat voice agents in 90+ languages
About Eleven v4 Turbo
Real-time text-to-speech for voice agents, Eleven v4 Turbo is the low-latency member of ElevenLabs' v4 family, released on 28 September 2026. It is built for phone and chat agents, where a reply has to start quickly enough to feel like a conversation. ElevenLabs puts inference at roughly 100 milliseconds at the median, with first speech arriving at about 150 milliseconds at the median. Those are the company's own figures, and no independent measurement was found when this was written.
The model is designed to bring v4's expressive delivery to latency-sensitive uses. It works with ElevenAgents, ElevenLabs' platform for conversational agents, and the standard API reaches it too.
Languages and expressive control
Like v4, the model supports more than 90 languages and accepts inline direction tags that shape emotion, accent and sound effects. A voice agent can therefore shape how a line is delivered without changing the underlying voice. Because the model is hosted only and no weights are published, it cannot be run on a customer's own hardware.
What to test before choosing it
The pages reviewed gave no per-character price, so cost has to be confirmed directly with ElevenLabs. Buyers building voice agents should check whether the latency holds on their own telephony route and in their own languages, because a vendor's median cannot show how the model behaves on that route or under real call load.
TrustList summary
Eleven v4 Turbo is the fast variant in ElevenLabs' v4 line, released on 28 September 2026. The company built it for latency-sensitive uses such as phone and chat agents, and says it brings the expressive delivery of v4 to real-time work. It runs with ElevenAgents, the company's conversational-agent platform, and is also available through the API.
What Eleven v4 Turbo does
- Low latency: a median inference latency of about 100 milliseconds, with about 150 milliseconds to first speech, as the company states.
- Expressive delivery: the same inline direction tags for emotion, accent and sound effects as v4.
- Language coverage: more than 90 languages.
- Agent platform: built to run with ElevenAgents, and available through the API.
Clients
Teams building phone and chat voice agents.
Key facts
- Released: 28 September 2026
- Access: hosted only, with no published weights
- Speed figures: the company's own, with no independent measurement found
Buyers should test the latency on their own telephony route and languages, because a vendor median cannot show how it holds up there.
Summary written by TrustList from the business's own published information, Nov 2026.
Benchmarks & AI stats
| Benchmark | Official | Community avg |
|---|---|---|
| No benchmark scores yet. Be the first to add one. | ||
“Official” values are editor-approved and feed the ranking. “Community avg” is the mean of member submissions (shown for transparency; it never affects the ranking until an editor approves a value).
Sign in to add a benchmark score for this model.
Eleven v4 Turbo launches
Trust Score
An earned signal from verification, reviews, awards, transparency and engagement - the vendor can't buy it.
Updated 10/3/2026
What the business tells TrustList
- Founded
- 2026 (0 years) evidence sent
Request a demo or quote from Eleven v4 Turbo
Reviews
Write the first review of Eleven v4 Turbo
Used it? Your experience helps other buyers decide.
Write a reviewQuestions & answers
No questions yet. Be the first to ask about Eleven v4 Turbo.
Eleven v4 Turbo alternatives
Similar listings buyers compare against this one.
Open-weight translation model from Bilibili's Index team, covering 150 languages and following glossary and style instructions
Aleph Alpha's open-weight English-German mixture-of-experts model for self-hosting, released under Apache 2.0 in October 2026
Microsoft AI's text-to-speech model for keeping one voice across 23 languages, with voice cloning from short audio
Microsoft AI's real-time speech-to-text model for voice agents, transcribing 60 languages with continuous language detection
Anthropic's smallest and fastest Claude 5.5 model, available on its own API and three cloud platforms
Google's open multimodal embedding model that maps text, images, audio and video into one vector space, under Apache 2.0
Perplexity's open-weight decision model that picks among given options for routing and checks in AI systems
More on TrustList
Everything here links back to the same verified catalogue. Pick your next stop.
- Write a reviewHelp other buyers decide
- CompaniesAgencies, consultancies and IT service providers, ranked by verified reviews.
- ProductsSoftware and SaaS with pricing, features, integrations and alternatives.
- ArticlesGuides, comparisons and research from the editorial desk and the community.
- AwardsAnnual recognition decided by verified reviews and an independent jury.
- LaunchesNew products and releases, voted up by the community every day.
- RequestsBuyers describe what they need; vendors respond directly.
- PeopleReviewers, authors and makers with public profiles.
- ComparePut up to four listings side by side before you shortlist.