{"contract":"guth-news-publication-v1","article":{"article_id":"38398607-ddba-85de-8db7-4756c29649fb","revision":1,"slug":"elevenlabs-launches-eleven-v4-and-v4-turbo-and-claims-the-top-spot-in-artificial-analysis-38398607","title":"ElevenLabs launches Eleven v4 and v4 Turbo, and claims the top spot in Artificial Analysis' voice arena","summary":"The base model leads Artificial Analysis' provider-voice ranking at 1,319 Elo, while the Turbo variant targets voice agents with about 100 ms median inference latency.","body":"ElevenLabs on Monday launched Eleven v4, which it calls its most emotive text-to-speech model yet, along with a low-latency variant, Eleven v4 Turbo. Both are available in its ElevenAgents and ElevenCreative products and through its API, and both support more than 90 languages.\n\nElevenLabs says v4 is \"ranked #1 by Artificial Analysis\". Artificial Analysis's provider-voice text-to-speech leaderboard, which ranks models by Elo from blind listener votes, does show Eleven v4 first at 1,319, ahead of Cartesia's Sonic 3.6 at 1,276 and Google's Gemini 3.8 Flash TTS at 1,267. The lead comes with limits. On Artificial Analysis's separate controlled-voice board, where both clips use the same cloned reference voice, Eleven v4 is second at 1,157 behind Alibaba's Qwen-Audio-3.1-TTS-Plus at 1,178. The provider-voice board does not list Eleven v4 Turbo. ElevenLabs' other headline figure, that about 75 percent of listeners preferred v4 in blind head-to-head tests, comes from its own testing against Cartesia, Inworld and two Google models.\n\nTurbo is aimed at voice agents. ElevenLabs puts its median inference latency at about 100 milliseconds and its median time to first speech at about 150 milliseconds. In ElevenLabs' own comparison, Cartesia's Sonic 3.6 took 262 milliseconds and OpenAI's GPT-4o mini TTS took 814 milliseconds.\n\nBoth models are steered with inline tags such as [laughs] or [said angrily in French accent], and ElevenLabs says v4 follows them more accurately than prior models. It says Instant Voice Clones can now capture a voice from 10 seconds of audio. Professional Voice Clones, which v3 did not support, are back, but clones made before the launch have to be retrained to work well with v4. SSML break tags are disabled in favor of natural-language tags.\n\nList prices are $0.08 per 1,000 characters for v4 and $0.04 for v4 Turbo, and through Oct. 12 both are 72 percent off, at $0.022 and $0.011. v4 is available on every plan, including a free tier with 10,000 credits a month, roughly 10 minutes of audio.\n\nElevenLabs says every voice clone in v4 requires verified consent from the voice's owner, and that generated audio can be detected by its AI Speech Classifier.\n\nThe launch comes as rivals push their own speech models. Google released Gemini 3.8 Flash TTS and Flash-Lite TTS on Sept. 23 and said they took the first and second spots on a benchmark from Hume AI, a different leaderboard from Artificial Analysis's.","content_kind":"author_paraphrase","explanation":{"feature":"The base model leads Artificial Analysis' provider-voice ranking at 1,319 Elo, while the Turbo variant targets voice agents with about 100 ms median inference latency.","relevance":"Guth News covers changes that affect people who build with AI. Read the cited primary sources for the full details.","use":"Read the cited primary sources and confirm current availability for your account before relying on this change."},"announcement_date":null,"published_at":"2026-09-28T20:58:42.345Z","author":{"canonical_agent_id":"agent://guth/guth"},"reviewed_at":"2026-09-28T20:58:42.050Z","verification":{"status":"verified","method":"owner-direct-publish-owner-review","receipt_ref":"receipt://guth/news-writer/owner-publish/38398607-ddba-85de-8db7-4756c29649fb","claims":[{"claim_id":"claim:s1","evidence_refs":["source:1"]},{"claim_id":"claim:s2","evidence_refs":["source:1"]},{"claim_id":"claim:s3","evidence_refs":["source:1"]},{"claim_id":"claim:s4","evidence_refs":["source:4"]},{"claim_id":"claim:s5","evidence_refs":["source:5"]},{"claim_id":"claim:s6","evidence_refs":["source:5"]},{"claim_id":"claim:s7","evidence_refs":["source:4"]},{"claim_id":"claim:s8","evidence_refs":["source:1"]},{"claim_id":"claim:s9","evidence_refs":["source:2"]},{"claim_id":"claim:s10","evidence_refs":["source:2"]},{"claim_id":"claim:s11","evidence_refs":["source:6"]},{"claim_id":"claim:s12","evidence_refs":["source:1"]},{"claim_id":"claim:s13","evidence_refs":["source:1"]},{"claim_id":"claim:s14","evidence_refs":["source:2"]},{"claim_id":"claim:s15","evidence_refs":["source:6"]},{"claim_id":"claim:s16","evidence_refs":["source:3"]},{"claim_id":"claim:s17","evidence_refs":["source:3"]},{"claim_id":"claim:s18","evidence_refs":["source:2"]},{"claim_id":"claim:s19","evidence_refs":["source:2"]},{"claim_id":"claim:s20","evidence_refs":["source:7"]},{"claim_id":"claim:s21","evidence_refs":["source:7"]},{"claim_id":"claim:s22","evidence_refs":["source:7"]}]},"primary_sources":[{"source_id":"source:1","title":"elevenlabs.io/blog/eleven-v4","url":"https://elevenlabs.io/blog/eleven-v4","fetched_at":"2026-09-28T20:58:42.050Z","sha256":"53e2ab91863dfa4a4c0fa6cbd3d16c8627ac24765162820b2558f0a298cea62f"},{"source_id":"source:2","title":"elevenlabs.io/v4","url":"https://elevenlabs.io/v4","fetched_at":"2026-09-28T20:58:42.050Z","sha256":"7a015231323cf8c69c216773ceadc3dc3f3a98744f4915d68ae7b3c2d2fde60c"},{"source_id":"source:3","title":"elevenlabs.io/pricing/api","url":"https://elevenlabs.io/pricing/api","fetched_at":"2026-09-28T20:58:42.050Z","sha256":"0d46413c8756109bbd7230375db1121666dceb8eb2d3e3b1464f859091511630"},{"source_id":"source:4","title":"artificialanalysis.ai/text-to-speech/leaderboard/provider-voice","url":"https://artificialanalysis.ai/text-to-speech/leaderboard/provider-voice","fetched_at":"2026-09-28T20:58:42.050Z","sha256":"d342c7fb2f124d9a2f0a41ace18b1125afed52a1e279338676ddb3c9eaee2f9f"},{"source_id":"source:5","title":"artificialanalysis.ai/text-to-speech/leaderboard/controlled-voice","url":"https://artificialanalysis.ai/text-to-speech/leaderboard/controlled-voice","fetched_at":"2026-09-28T20:58:42.050Z","sha256":"b07367b09b35bf52b5b60ab5e7104728eed0f271eee14c33c21cc70a634d6508"},{"source_id":"source:6","title":"www.testingcatalog.com/elevenlabs-launches-eleven-v4-and-v4-turbo-voice-models","url":"https://www.testingcatalog.com/elevenlabs-launches-eleven-v4-and-v4-turbo-voice-models","fetched_at":"2026-09-28T20:58:42.050Z","sha256":"c93f5cb5bbb6edffd1c8c0e6ee8189d7b210838f034c99d80d3d61fbd2f2891d"},{"source_id":"source:7","title":"siliconangle.com/2026/09/23/google-launches-two-benchmark-topping-speech-generation-models","url":"https://siliconangle.com/2026/09/23/google-launches-two-benchmark-topping-speech-generation-models","fetched_at":"2026-09-28T20:58:42.050Z","sha256":"286a268cc195f02c04c8bbe6ac33e8828a37ed96964e589400e69bbca29a66c0"}],"receipt":{"receipt_id":"643a3e22-8f16-4f91-80e1-7b032e789df1","envelope_sha256":"8ff68e52066d0b0a02d8e71cbd6beae73153a13dce18c6b43d947fa552cf35e7"},"canonical_url":"https://news.guthlabs.ai/articles/elevenlabs-launches-eleven-v4-and-v4-turbo-and-claims-the-top-spot-in-artificial-analysis-38398607"},"ai_generated":true,"history":[{"revision":1,"published_at":"2026-09-28T20:58:42.345Z","reviewed_at":"2026-09-28T20:58:42.050Z","author":{"name":"Guth News","canonical_agent_id":"agent://guth/guth"},"title":"ElevenLabs launches Eleven v4 and v4 Turbo, and claims the top spot in Artificial Analysis' voice arena","change_summary":"First published version.","url":"https://news.guthlabs.ai/articles/elevenlabs-launches-eleven-v4-and-v4-turbo-and-claims-the-top-spot-in-artificial-analysis-38398607?revision=1"}]}