On September 28, ElevenLabs released two voice models at once: Eleven v4, its most expressive text-to-speech model, and Eleven v4 Turbo, the realtime variant aimed at agents. The goal of this generation is no longer "reading text like a human" but "performing it" — interpreting tone, emotion, pacing and context while preserving the speaker's identity. The TTS race is shifting from pure synthesis quality to a two-axis contest of expressiveness and latency.

Three concrete upgrades from the new architecture

The official announcement states that Eleven v4 is built on an entirely new architecture. In verifiable specs:

  • Languages grow from 70+ to 90+: Eleven v3 supported 70+ languages; the v4 family covers 90+, including Mandarin and Cantonese.
  • Double the per-request limit: Eleven v4 handles 10,000 characters per request (about 10 minutes of audio) versus 5,000 for v3 — a direct win for long-form audiobooks.
  • Better voice cloning: instant clones now need just 10 seconds of audio and, per the company, outperform the Professional Voice Clones of the Multilingual v2 era; Professional Voice Clones, absent in v3, return with the model's full emotional range. Every clone requires verified consent from the voice's owner, and generated audio can be flagged by ElevenLabs' AI Speech Classifier.

On the API side, v4 ships via the Text to Dialogue API with natural multi-speaker dialogue, while Turbo streams over a WebSocket channel.

100 milliseconds is the battleground for voice agents

The headline number for v4 Turbo is a median inference latency of about 100ms — in the company's words, faster than the average pause between two people talking. In ElevenLabs' September WebSocket benchmark (identical scripts, default settings, network latency removed), Turbo reached a median time to first speech of roughly 150ms, against 262ms for Cartesia Sonic 3.6 and 814ms for OpenAI GPT-4o mini TTS. Treat these as vendor-run numbers: the ordering is informative, and the exact figures need third-party replication.

The engineering direction matters more: ElevenLabs says it optimized v4 Turbo and its ElevenAgents platform together as one system. That means the model ships bound to the runtime — agent latency was never just a model problem, and architectures that stitch third-party TTS together are structurally disadvantaged. That is exactly where ElevenLabs is positioning.

First on the blind arena, and a pricing probe

On Artificial Analysis's blind-vote Speech Arena, Eleven v4 ranks first at Elo 1319, ahead of Cartesia Sonic 3.6 (1276) and Google Gemini 3.8 Flash TTS (1267). On pricing, per a third-party roundup, Eleven v4 costs 2.2 US cents per 1,000 characters during the intro period ($0.011 for Turbo), reverting to $0.08 and $0.04 after October 12.

So what

The signal from this launch: quality gaps are now quantified by blind arenas, and ElevenLabs held the top spot with an architecture change — but Cartesia and Google are right behind, with no generational gap. The thing to watch is the "model + agent runtime" bundle: once voice latency enters the 100ms class, the decisive factor moves from model parameters to system-level optimization. The question for competitors: where is your agent stack?

Sources: ElevenLabs blog, official model docs, Unite.AI.