Elevenlabs

ElevenLabs-v3

Generally availableProprietary128K context

Summary

ElevenLabs-v3 is a proprietary speech model from Elevenlabs, released on 20 Aug 2025. It accepts text and generates audio, with a 128K-token context window.

Expressive text-to-speech model with inline audio tags across 70+ languages

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperElevenlabs
Release date20 Aug 2025 [models.dev]
StatusGenerally available [models.dev]
WeightsProprietary (API only) [models.dev]
Context window128K (128,000 tokens) [models.dev]
InputText [models.dev]
OutputAudio [models.dev]
Reasoning modeNo [models.dev]
Tool callingYes [models.dev]

ElevenLabs-v3 API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of ElevenLabs-v3?

ElevenLabs-v3 has a context window of 128,000 tokens (128K), according to models.dev.

Is ElevenLabs-v3 open source?

No. ElevenLabs-v3 is a proprietary model; Elevenlabs has not released its weights.

When was ElevenLabs-v3 released?

Elevenlabs released ElevenLabs-v3 on 20 Aug 2025, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Gemini 2.5 Flash TTSGoogle DeepMind30 Sept 202533K$0.50$10Closed
Gemini 2.5 Pro TTSGoogle DeepMind30 Sept 202533K$1$20Closed
Grok TTSxAI16 Mar 202615K––Closed
Grok Voice TTS 1.0xAI31 Jul 202615K––Closed
Canopy Labs Orpheus Arabic SaudipreviewCanopylabs16 Dec 20254K––Closed
MiMo-V2.5-TTSXiaomi (MiMo)22 Apr 20268K––Closed

Change history

  • Added to the directory

Sources