Eleven v4 API
Eleven v4 text to speech — ElevenLabs' most expressive model, 90+ languages, billed on input length.
ElevenLabs' most expressive text-to-speech model. Inline audio tags direct emotion and delivery, across 90+ languages and up to 10,000 characters per request.
No credit card required. Takes 30 seconds.
Eleven v4 API pricing
Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated October 23, 2026.
| Billing | Price |
|---|---|
| Rate | $0.1688/1K chars |
| What it costs | Per job |
|---|---|
| Short reply200 characters | $0.034 |
| Blog post narration10,000 characters (~1,600 words) | $1.69 |
| Audiobook chapter100,000 characters | $16.88 |
2,400+
Developers
1.2M+
API calls served
100+
Endpoints
$0.01
Per call
Yep, that's it.
Playground coming soon — use the API endpoint directly with your API key.
Eleven v4 specs
| Provider | ElevenLabs |
|---|---|
| Model ID | elevenlabs/eleven-v4 |
| Endpoint | /v1/media/queue |
| Type | Text to Speech |
| Output formats | mp3 |
| Voices | 21 presets (default sarah) |
How to get an Eleven v4 API key
- 1
Create a free account
Sign up at yepapi.com with Google or email. It takes about 30 seconds and needs no card.
- 2
Create an API key
Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.
- 3
Call Eleven v4
Send a request to /v1/media/queue with the x-api-key header and model "elevenlabs/eleven-v4".
- 4
Pay as you go
Usage is billed per request from your balance. Top up any amount; there is no subscription.
Strengths
Eleven v4 is ElevenLabs' most expressive model, for reads that need real emotional range.
Tags written into the text control emotion and delivery mid-passage.
One model covers more than 90 languages without switching providers.
Long passages fit in a single request.
Quick start
Copy this snippet and start making calls with Eleven v4.
// Step 1: Submit job
const res = await fetch('https://api.yepapi.com/v1/media/queue', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "elevenlabs/eleven-v4",
"prompt": "I wasn't going to say anything. [sighs] But you deserve to hear it from me first — we did it. We actually did it.",
"options": {
"voice": "sarah"
}
}),
});
const { data } = await res.json();
const jobId = data.jobId;
// Step 2: Poll for result
const status = await fetch(`https://api.yepapi.com/v1/media/status/${jobId}`, {
headers: { 'x-api-key': 'YOUR_API_KEY' },
});
const { data: job } = await status.json();
// job.status: "pending" | "processing" | "completed" | "failed"
// job.result: { text?, image?, audio?, video? }Eleven v4 vs similar models
Every model below runs on the same API key — switch by changing the model ID.
| Model | Provider | Price |
|---|---|---|
| Eleven v4 | ElevenLabs | $0.1688/1K chars |
| Eleven Flash v2.5 | ElevenLabs | $0.0844/1K chars |
| Eleven Flash v2 | ElevenLabs | $0.0844/1K chars |
| Eleven Turbo v2.5 | ElevenLabs | $0.0844/1K chars |
| Eleven Turbo v2 | ElevenLabs | $0.0844/1K chars |
| Eleven v3 Conversational | ElevenLabs | $0.0844/1K chars |
| Kokoro 82M | hexgrad | $0.0014/1K chars |
| Fish Audio Drama 3 | Fish Audio | $0.0042/1K chars |
Why use Eleven v4 through YepAPI?
Eleven v4 API — ElevenLabs' most expressive speech model
Eleven v4 is ElevenLabs' most expressive text-to-speech model. Inline audio tags give emotional and delivery control, it supports more than 90 languages, and a single request can carry up to 10,000 characters.
Through YepAPI you submit text to `/v1/media/queue`, poll the job, and download the audio — one key, billed on input length at $0.1688 per 1,000 characters.
Start generating in 30 seconds
$5 free credit on signup. No credit card required. Pay per call.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
ElevenLabs' most expressive text-to-speech model. Inline audio tags direct emotion and delivery, across 90+ languages and up to 10,000 characters per request.
Eleven v4 costs $0.1688/1K chars through YepAPI, billed per request with no monthly fee. For example, a short reply (200 characters) costs about $0.034.
Sign up at yepapi.com (Google or email, about 30 seconds), open the dashboard and create an API key. The same key works for Eleven v4 and every other model — no separate ElevenLabs account or waitlist.
New YepAPI accounts in most countries get free signup credit, enough to test Eleven v4 without a card. After that you pay per request at the rates above — there is no subscription.
Use "elevenlabs/eleven-v4" as the model on /v1/media/queue. The short alias "elevenlabs" also works.
Ready to use Eleven v4?
$5 free credit on signup. No credit card required. Pay per call.
Explore more models
Eleven v3 Conversational
ElevenLabsEleven v3 Conversational text to speech — Eleven v3 tuned for conversational agents, billed on input length.
Eleven Flash v2
ElevenLabsEleven Flash v2 text to speech — ultra-low-latency English speech, billed on input length.
Eleven v3
ElevenLabsEleven v3 text to speech — emotionally rich speech with audio tags, 70+ languages, billed on input length.
Qwen-Audio 3.0 TTS Flash
QwenQwen-Audio 3.0 TTS Flash text to speech — fast Chinese & English speech, billed on input length.
Sesame CSM 1B
SesameSesame CSM 1B text to speech — conversational speech for assistants, billed on input length.
HeyGen Voice
HeyGenHeyGen Voice text to speech — 10 built-in voices, 44.1 kHz PCM, billed on input length.
More Text to Speech models
- Deepgram Flux TTS API · Deepgram
- Gemini 3.1 Flash TTS API · Google
- Kokoro 82M API · hexgrad
- MAI-Voice-2.1 API · Microsoft
- Voxtral Mini TTS API · Mistral
- Gemini 3.8 Flash Lite TTS API · Google
- Voxtral TTS 3 API · Mistral
- Gemini 3.8 Flash TTS API · Google
- Deepgram Aura-2 API · Deepgram
- Fish Audio S1 API · Fish Audio
- Seed Audio 1.0 API · ByteDance
- Eleven v4 Turbo API · ElevenLabs