ElevenLabs v4 Turbo is the low-latency variant of Eleven v4: the same expressive voices and audio tags in 90+ languages, tuned for real-time use.
| Developer | ElevenLabs |
|---|---|
| Model ID | elevenlabs/eleven_v4_turbo |
| Modalities | Text → Audio |
| Languages | 90+ |
| Released | 28 September 2026 |
| Endpoint | POST /v1/tts |
Built for real time
The low-latency variant of v4, for agents and live conversation where the wait before audio starts is what the listener notices.
Same voices and tags
Expressive delivery and inline audio tags carry over from v4, in the same 90+ languages.
Half the price of v4
$52 against $104 per 1M characters, which changes the economics of speech on every turn of a dialogue.
Voice agents
Support lines and in-app assistants that answer immediately.
Interactive characters
Games and companions where speech is generated turn by turn.
Sources: https://elevenlabs.io/docs/models · https://elevenlabs.io/pricing/api
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
import requests r = requests.post( "https://api.aimlapi.com/v1/tts", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "elevenlabs/eleven_v4_turbo", "text": "Hello from AI/ML API", "voice": "Rachel" }, ) print(r.json()["audio"]) # URL to the generated audio
const r = await fetch("https://api.aimlapi.com/v1/tts", { method: "POST", headers: { Authorization: "Bearer " + process.env.AIMLAPI_KEY, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "elevenlabs/eleven_v4_turbo", "text": "Hello from AI/ML API", "voice": "Rachel" }), }); console.log((await r.json()).audio);
curl -X POST https://api.aimlapi.com/v1/tts \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"elevenlabs/eleven_v4_turbo","text":"Hello from AI/ML API","voice":"Rachel"}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
Billed per character of input text.
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| TTS Arena | 1334 | Human preference Elo from blind pairwise listening comparisons of speech samples, measured independently by Artificial Analysis | Source | October 6, 2026 |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Eleven v4 Turbo This page | Speech synthesis | |||
| Speech synthesis | ||||
| Speech synthesis |
Eleven v4 Turbo is ElevenLabs' text-to-speech model for real-time use, described by the vendor as its most emotive real-time speech synthesis model. It is intended for agents and live conversation.
$14.3 per 1M characters through AI/ML API — half the price of Eleven v4. Speech models are billed by characters of input text.
Text in, audio out. You pass the text and a voice, and the response carries a URL to the generated audio.
Real-time speech: voice agents, live assistants, and anything where the wait before audio starts matters more than the last increment of quality.
The text-to-speech endpoint, POST /v1/tts, with model set to elevenlabs/eleven_v4_turbo.
