--- title: ElevenLabs releases v4 and v4 Turbo speech models with... description: ElevenLabs shipped two new text-to-speech models, Eleven v4 and v4 Turbo, adding automatic expression control that adjusts tone, pacing, and emotion across... canonical: https://daily.dev/posts/elevenlabs-releases-v4-and-v4-turbo-speech-models-with-expression-control-and-90-language-support-da1hwlv5m twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: ElevenLabs releases v4 and v4 Turbo speech models with expression control and 90-language support | daily.dev og:description: ElevenLabs shipped two new text-to-speech models, Eleven v4 and v4 Turbo, adding automatic expression control that adjusts tone, pacing, and emotion across... og:url: https://daily.dev/posts/elevenlabs-releases-v4-and-v4-turbo-speech-models-with-expression-control-and-90-language-support-da1hwlv5m og:image: https://api.daily.dev/og/posts/da1HwLv5M.png og:image:alt: ElevenLabs releases v4 and v4 Turbo speech models with expression control and 90-language support og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # ElevenLabs releases v4 and v4 Turbo speech models with expression control and 90-language support **[Collections](https://daily.dev/sources/collections)** · 1 min read · 1 upvotes · 0 comments ## Summary ElevenLabs shipped two new text-to-speech models, Eleven v4 and v4 Turbo, adding automatic expression control that adjusts tone, pacing, and emotion across longer passages, expanding language support from 70 to over 90 languages (with notable gains in Japanese, Brazilian Portuguese, Mandarin, and Cantonese), and enabling voice cloning from just 10 seconds of audio. v4 Turbo targets lower latency for voice agents. v4 took the top spot on the Artificial Analysis Provider Voice TTS Arena. The release lands in a crowded market against Cartesia, Deepgram, Fish Audio, Boson, WellSaid Labs, Google, and OpenAI, though ElevenLabs' enterprise calling revenue now exceeds $600 million annualized. ## Content ElevenLabs released two new speech models this week: Eleven v4 and Eleven v4 Turbo. The v4 model immediately took the top spot on the Artificial Analysis Provider Voice TTS Arena, which is a reasonable signal that the quality jump is real. The headline improvements: - **Expression control** - v4 tracks context across longer passages to adjust tone, pacing, and emotion automatically, building on the inline expression tags introduced in v3 - **Language support** expanded from 70 to over 90 languages, with the most noticeable quality gains in Japanese, Brazilian Portuguese, Mandarin, and Cantonese - **Voice cloning** now works from as little as 10 seconds of audio - **v4 Turbo** targets lower latency for voice agent use cases The company describes v4 as built on a new architecture designed to generate speech with "the intended tone, pacing, emotion, and character" - which is a reasonable way to describe what expression-aware TTS actually needs to do. The release comes at a crowded moment. ElevenLabs is competing against Cartesia, Deepgram, Fish Audio, Boson, WellSaid Labs, and voice products from Google and OpenAI. Despite that, the company's enterprise calling business keeps growing - annualized revenue is now over $600 million. ## Questions this post answers ### What's new in ElevenLabs v4 compared to previous versions? Eleven v4 adds automatic expression control that tracks context across longer passages to adjust tone, pacing, and emotion, building on the inline expression tags from v3. Language support expanded from 70 to over 90 languages, with notable quality gains in Japanese, Brazilian Portuguese, Mandarin, and Cantonese. Voice cloning now works from as little as 10 seconds of audio, and v4 took the top spot on the Artificial Analysis Provider Voice TTS Arena. _Developers evaluating TTS providers can track model releases like this one on daily.dev._ ### What is Eleven v4 Turbo designed for? Eleven v4 Turbo is a lower-latency variant of ElevenLabs' v4 speech model, built specifically for voice agent use cases where response speed matters more than maximum fidelity. It ships alongside the standard v4 model, which focuses on expression control, expanded language coverage, and improved voice cloning from short audio samples. _Teams building latency-sensitive voice agents can follow speech model updates on daily.dev._ ## Similar posts on daily.dev - [Cartesia vs ElevenLabs: Choosing a Voice API in 2026](https://daily.dev/posts/cartesia-vs-elevenlabs-choosing-a-voice-api-in-2026-yndcz4bmk) · Medium · 0 upvotes · 0 comments - [ElevenLabs v3 Text-to-Speech on DigitalOcean Inference](https://daily.dev/posts/elevenlabs-v3-text-to-speech-on-digitalocean-inference-qekzeoxov) · DigitalOcean Community · 0 upvotes · 0 comments --- Tags: [#ai-agents](https://daily.dev/tags/ai-agents), [#deep-learning](https://daily.dev/tags/deep-learning), [#text-to-speech](https://daily.dev/tags/text-to-speech), [#voice-cloning](https://daily.dev/tags/voice-cloning), [#elevenlabs](https://daily.dev/tags/elevenlabs) [View this post on daily.dev](https://daily.dev/posts/elevenlabs-releases-v4-and-v4-turbo-speech-models-with-expression-control-and-90-language-support-da1hwlv5m) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"ElevenLabs releases v4 and v4 Turbo speech models with expression control and 90-language support","url":"https://daily.dev/posts/elevenlabs-releases-v4-and-v4-turbo-speech-models-with-expression-control-and-90-language-support-da1hwlv5m","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/elevenlabs-releases-v4-and-v4-turbo-speech-models-with-expression-control-and-90-language-support-da1hwlv5m"},"datePublished":"2026-09-28T16:56:46.613Z","dateModified":"2026-09-28T16:57:20.968Z","description":"ElevenLabs shipped two new text-to-speech models, Eleven v4 and v4 Turbo, adding automatic expression control that adjusts tone, pacing, and emotion across...","isAccessibleForFree":true,"articleSection":"Collections","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Collections","logo":"https://media.daily.dev/image/upload/s--fk_6ycEi--/f_auto,q_auto/v1780996001/logos/collections?_a=BAMAMiWQ0","url":"https://daily.dev/sources/collections"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/elevenlabs-releases-v4-and-v4-turbo-speech-models-with-expression-control-and-90-language-support-da1hwlv5m","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":1},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"ai-agents,deep-learning,text-to-speech,voice-cloning,elevenlabs","timeRequired":"PT1M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Collections","item":"https://daily.dev/sources/collections"},{"@type":"ListItem","position":3,"name":"ElevenLabs releases v4 and v4 Turbo speech models with expression control and 90-language support"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/elevenlabs-releases-v4-and-v4-turbo-speech-models-with-expression-control-and-90-language-support-da1hwlv5m#faq","mainEntity":[{"@type":"Question","name":"What's new in ElevenLabs v4 compared to previous versions?","acceptedAnswer":{"@type":"Answer","text":"Eleven v4 adds automatic expression control that tracks context across longer passages to adjust tone, pacing, and emotion, building on the inline expression tags from v3. Language support expanded from 70 to over 90 languages, with notable quality gains in Japanese, Brazilian Portuguese, Mandarin, and Cantonese. Voice cloning now works from as little as 10 seconds of audio, and v4 took the top spot on the Artificial Analysis Provider Voice TTS Arena. Developers evaluating TTS providers can track model releases like this one on daily.dev."}},{"@type":"Question","name":"What is Eleven v4 Turbo designed for?","acceptedAnswer":{"@type":"Answer","text":"Eleven v4 Turbo is a lower-latency variant of ElevenLabs' v4 speech model, built specifically for voice agent use cases where response speed matters more than maximum fidelity. It ships alongside the standard v4 model, which focuses on expression control, expanded language coverage, and improved voice cloning from short audio samples. Teams building latency-sensitive voice agents can follow speech model updates on daily.dev."}}]} ```