How fast does Eleven v4 Turbo start speaking?

ElevenLabs says Turbo starts producing audible speech in 150 milliseconds. That compares with 262 milliseconds for Cartesia Sonic 3.6 and 814 milliseconds for OpenAI's GPT-4o mini TTS, according to the company's tests.

How much does Eleven v4 cost?

Standard API pricing is $80 per million characters for v4 and $40 for Turbo. Through October 12, those rates fall to $22 and $11. Users on the $22 monthly Creator plan or higher can use v4 in ElevenCreative at no extra cost for two weeks, capped at twice their monthly credits.

How many languages does Eleven v4 support?

The new version supports more than 90 languages. That is up from about 70 with v3.

Audio & SpeechTHE DECODER23h agoSep 30, 2026, 01:00 JST

Eleven v4 lands with a fast Turbo mode for voice agents

Send on LINE

3 Key Points

What happened
ElevenLabs released Eleven v4, which handles up to 10,000 characters per request and supports more than 90 languages, up from about 70 in v3.
Why it matters
More reliable direction-following and voice consistency could make v4 practical for longer productions like audiobooks, dubbing, and multi-line scenes, not just short clips.
What to watch
The company's performance and preference numbers come from its own tests and benchmarks, so independent results will matter. Standard pricing is $80 per million characters, with a temporary cut to $22 through October 12.

WHO IT HITSVoice-product teams — developers building real-time agents, audiobook and dubbing producers, and voice actors licensing clones — are the ones affected, since Turbo targets low-latency agents and v4 targets long-form consistency.

Not sure about something? Ask the AI

Questions and answers are published on this page.

Summaries like this, in your inbox every morning.

Get news like this every morning, free

Context & Analysis

Eleven v4 is the successor to v3, released just over a year ago, which already supported audio tags but followed them less accurately. With v4, the company says a new architecture analyzes a script's tone, pacing, and context, while users set pronunciation through phonetic spelling. ElevenLabs reports 91.7 percent on a pronunciation benchmark, up from 85.6 percent for v3, and about three-quarters of listeners in its blind tests preferred v4 over models from Cartesia, Inworld, and Google.

On Artificial Analysis' Provider Voice Arena leaderboard, v4 ranks ahead of Cartesia Sonic 3.6 and Google's Gemini 3.8 Flash TTS. Professional Voice Clones, which were unsupported in v3 and are available again in v4, reflect a focus on production uses like dubbing and audiobooks. Both models are available now in ElevenAgents, ElevenCreative, and through the API, while ElevenLabs separately released its Music 2.5 model in mid-September.

FAQ

How fast does Eleven v4 Turbo start speaking?: ElevenLabs says Turbo starts producing audible speech in 150 milliseconds. That compares with 262 milliseconds for Cartesia Sonic 3.6 and 814 milliseconds for OpenAI's GPT-4o mini TTS, according to the company's tests.
How much does Eleven v4 cost?: Standard API pricing is $80 per million characters for v4 and $40 for Turbo. Through October 12, those rates fall to $22 and $11. Users on the $22 monthly Creator plan or higher can use v4 in ElevenCreative at no extra cost for two weeks, capped at twice their monthly credits.
How many languages does Eleven v4 support?: The new version supports more than 90 languages. That is up from about 70 with v3.

THE DECODERRead Original Article

Send on LINE

AI news that matters for your work, in one minute a day

Pick your industry and the AI tools you use, and get news related to your work every day.

Get it free

Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.