ElevenLabs

ElevenLabs · United Kingdom (London) · Speech & audio
Global Closed sourceFree tier
Showing version: Eleven v3 · 2025-06-03 · Version lineage ↓
Eleven v3Eleven Multilingual v2ElevenLabs 公测首发(英文 v1 系)
01

Overview

ElevenLabs' voice AI platform built on expressive TTS model lines (Multilingual v2, the low-latency Flash/Turbo lines and flagship Eleven v3), plus voice cloning, dubbing and Scribe speech-to-text, sold via credit-based subscriptions and API pricing.

Release date2025-06-03
02 / Provenance

Field checks and source notes

When sources disagree on a field, every reading is listed here with its own citation. We do not take a midpoint, invent a missing figure, or decide which side is right — follow the citation and judge for your case.

These field-level notes are recorded verbatim in Chinese in the source data. Open the Chinese version

03 / Plain layer

Plain-language benchmarks

Naturalness Not disclosed
Accuracy (WER) Not disclosed
Speed / latency Not disclosed
Languages supported Not disclosed
Price / free Not disclosed免费版 10,000 积分/月(约 10 分钟 TTS,非商用)
04

Practical facts

Context lengthNot disclosed
Max outputNot disclosed
ParametersNot disclosed
InputNot disclosed
Output priceNot disclosed
CNYNot disclosed
Free tierFree plan: 10,000 credits per month (about 10 minutes of TTS, non-commercial).
Output speedNot disclosed
Release date
LicenseNot disclosed
Show technical data

Technical benchmark table

No verified benchmark data (not tested / not disclosed / not applicable).
05

Version lineage

Back to family page →
VersionRelease dateStatus OpennessParametersWhat changed Detail
Eleven v3Showing version Active Closed source Not disclosed Flagship expressive model: debuted as an alpha research preview on 2025-06-03 with audio tags, multi-speaker dialogue and 70+ languages; public API on 2025-08-20 and GA on 2026-02-02. Detail
Eleven Multilingual v2 Active Closed source Not disclosed Launched as ElevenLabs exited beta, with synthesis in nearly 30 languages preserving cloned-speaker accents; still the stable workhorse for long-form narration. Detail
ElevenLabs 公测首发(英文 v1 系) Superseded Closed source Not disclosed Public beta debut of the platform, initially with English and Polish. Detail

Last updated: · Sources on detail page

06 / Compare

Comparable in this category

Cartesia Sonic
Whisper
Tongyi Speech (CosyVoice)
Doubao Speech
0 / 3 Compare Open comparison →