Eleven v4 Turbo

A low-latency speech model for assistants and interactive characters that need an expressive speaking voice.

Plain-English overview

What Eleven v4 Turbo actually is

Eleven v4 Turbo streams speech from text over a dialogue WebSocket. It is the voice layer of an application, not a replacement for its reasoning model or speech recognizer.

It shares the v4 family's voice-cloning and audio-tag controls. Use it when fast spoken replies matter; compare the standard model when producing finished narration.

Good fit for

Voice assistants
Interactive characters
Multilingual support agents

Category comparison

The facts that matter for voice models

These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.

Price basis: $0.04 / 1,000 charactersToken-, character-, or minute-based price for the listed access route.
Interaction mode: Realtime text-to-speech / text-to-dialogueSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior.
Published latency: ~100ms median inference (provider-reported)Provider-published measurement with its stated exclusions; not a Cody test.
Languages: 90+ languagesProvider-documented language coverage or a clear unpublished marker.
Tools & control: Audio tags, voice cloning and pronunciation dictionariesNative function calling, reasoning, or speech-control features.
Context or input limit: Not publishedDocumented token or character limit where it is meaningful.

API and provider access

Where to get Eleven v4 Turbo

ElevenLabsElevenLabs model docsOfficial TTS and realtime dialogue access.ElevenLabsRealtime dialogue WebSocketGenerate speech from text and selected voices.ElevenLabsElevenAPI pricingLive per-character pricing.

Availability

Regions and access stage

Available in ElevenCreative, ElevenAgents and ElevenAPI.

Default storage is US; enterprise isolated environments are offered in the EU, India, and Singapore, with processing caveats.

Check live availability

Data and training

The route matters.

This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.

Read the provider policy

Frequently asked questions

Eleven v4 Turbo FAQ

What is Eleven v4 Turbo?

A low-latency speech model for assistants and interactive characters that need an expressive speaking voice. Eleven v4 Turbo streams speech from text over a dialogue WebSocket. It is the voice layer of an application, not a replacement for its reasoning model or speech recognizer.

When was Eleven v4 Turbo released?

Eleven v4 Turbo was released on September 28, 2026 according to the cited provider materials.

Where can I access Eleven v4 Turbo?

Available in ElevenCreative, ElevenAgents and ElevenAPI. The access routes listed in this guide are ElevenLabs.

How much does Eleven v4 Turbo cost?

$0.04 / 1,000 characters. Standard API rate. Launch offer: $0.011 per 1,000 characters until October 12, 2026. Taxes and plan-specific terms are separate; confirm the current offer with ElevenLabs.

Where is Eleven v4 Turbo available?

Available in ElevenCreative, ElevenAgents and ElevenAPI. Default storage is US; enterprise isolated environments are offered in the EU, India, and Singapore, with processing caveats.

Is my Eleven v4 Turbo API data used for training?

ElevenLabs says enterprise customer data is not used for training by default. Other users can opt out of model improvement; enterprise zero-retention and regional environments are available with plan-specific limits. The policy belongs to the provider route and account terms, so verify it again before production use.

Related comparisons

Head-to-head comparisons

View category →