Eleven v3
ElevenLabs text-to-speech "turns text into lifelike audio with nuanced intonation, pacing and emotional awareness"; Eleven v3 is "Our most emotionally rich, expressive speech synthesis model", Multilingual v2 a "Lifelike, consistent quality speech synthesis model".
text → audio · made by ElevenLabs
$40per Mtok in
Vercel AI Gateway · 2 sellers
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| ElevenLabs api | standard | $100per million characterselevenlabs.io · read 2026-08-24 |
| Vercel AI Gateway aggregator | standard | $40per Mtok inai-gateway.vercel.sh · read 2026-10-29 |
Measured 1 standing
| Place | Board | Metric | Score |
|---|---|---|---|
| 20thof 42 | TTS Arena V2 | Elo | 1499 |
About
Eleven v3 — an audio model from ElevenLabs, sold by 2 companies from $40 per Mtok in, placed 20th of 42 on TTS Arena V2.
It takes text and returns audio. The catalogue files it under speak. Two companies sell it. The cheapest is $40 per Mtok in at Vercel AI Gateway. It stands 20th of 42 on TTS Arena V2.
Every current figure
- Maker
- ElevenLabs
- Register
- model
- Takes
- text
- Returns
- audio
- Licence
- not read
- Sellers
- 2
- Price
- $40 per Mtok in — Vercel AI Gateway
- Boards
- 1
- Best place
- 20th of 42 — TTS Arena V2
Known as 3 names
eleven-v3elevenlabs/eleven-v3Text-to-speech (v3 / Multilingual v2)