Speech Arena
Elo · text-to-speech arena
Custom pricing for production workloads
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.
elevenlabs/eleven_v4_turboPOST https://api.aimlapi.com/v1/ttsElevenLabs 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.
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
Human-preference results for Eleven v4 Turbo in speech arena, next to models available on AI/ML API. Data retrieved Nov 4, 2026.
Elo · text-to-speech arena
Arena results for models you can call with the same API key.
Listeners hear two clips of the same text and choose the more natural one. Eleven v4 Turbo ranks #2 of 101.
| Usage | Price | Unit |
|---|---|---|
| Input | $40 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Give your agent the model details, code and documentation.
export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"curl 'https://api.aimlapi.com/v1/tts' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "elevenlabs/eleven_v4_turbo",
"text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "elevenlabs/eleven_v4_turbo",
"text": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}
response = requests.post("https://api.aimlapi.com/v1/tts", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = 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": "Your order has shipped. It will arrive on Thursday between nine and eleven in the morning. Reply to this message if you need to change the delivery time."
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());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.
Eleven v4 Turbo costs $40 per 1M input tokens on AI/ML API, billed as you go with no subscription.
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.
Use elevenlabs/eleven_v4_turbo as the model parameter. Requests go to https://api.aimlapi.com/v1/tts with your AI/ML API key.