whatmodel.sh / tts / Eleven v4 Turbo

Eleven v4 Turbo

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Eleven v4 Turbo is a closed-weights text-to-speech model from ElevenLabs, released September 2026. Licence: proprietary.

Catalogue identity notes

ElevenLabs Eleven v4 Turbo, API model_id 'eleven_v4_turbo' (real-time variant), released 28 Sep 2026 per ElevenLabs' changelog ('Eleven v4 and Eleven v4 Turbo are now available'). The EMA Lightning card ran 'ElevenLabs v4 Turbo' itself with the default voice (George) and default settings. Distinct from elevenlabs-v3 and elevenlabs-v3-conversational.

Model information sources

Release date ↗

35.8±4.3#98 of 118 text-to-speech modelsfrom 1 benchmark result across 1 source* thinly tested, treat the rank as provisional

Score within the Vapi Humanness · Bradley–Terry rating, 2026-09-25 snapshot comparison set only.

$ how it compares

The text-to-speech models ranked either side of Eleven v4 Turbo, out of 148 with a score, then more from ElevenLabs.

#modelscorewhereRAMreleased
121Amphion VALL-E v2 recipe (MLS) Amphion (CUHK-Shenzhen)36±3local~2.9GB2024-06
122NeuTTS Air Neuphonic36±10local~4GB2025-10
123Eleven v4 Turbo ElevenLabs36±4api $40.00/M chars2026-09
124VITS (VCTK multi-speaker) Kakao Enterprise (Jaehyeon Kim et al.)34±5local~0.2GB2021-06
125Sesame CSM-1B Sesame34±5api $7.00/M chars +local~6.6GB2025-03
more from ElevenLabs
21Eleven v3 ElevenLabs65±1api $100.00/M chars2026-02
30Eleven Turbo v2.5 ElevenLabs64±4api $50.00/M chars2024-07
38Eleven Flash v2.5 ElevenLabs63±2api $50.00/M chars2024-12

see all text-to-speech models · find the ones that fit your machine

$ what it's good at

other tests1 not in a task · 93% of its score
testresultvs the others in its rundifficultycountswhy
Freya-TR-Eval Turkish TTS intelligibility (WER, faster-whisper large-v3, 8 kHz band)1.5% ✎▄········███ beats 1/6avg 0.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%typical

$ where to run it

Through an API

api · $40.00/M chars · elevenlabs.io ↗ · price sourceUSD per 1M input characters: ElevenLabs lists Eleven v4 Turbo Text to Speech at $0.04 per 1K characters (x1000), shown struck through with a launch promotion of $0.011 per 1K characters ('72% off until Oct 12'); the list rate is recorded. Product: ElevenAPI text to speech. API model: eleven_v4_turbo. Price basis: published list rate, per-1K to per-1M scaling only. Exclusions: subscription fees, taxes, the temporary promotion. Currency: USD. ElevenLabs official API pricing page, observed 2026-10-10.

$ how the score was worked out · EMA Lightning model card (can… 93%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
EMA Lightning model card (canberkkkkkk/ema-lightning), Benchmarks: Freya-TR-Eval1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 93%Apache-2.0
prior · pull toward the middle▇▇ 7%
weighted average= 35.8

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json