YepAPI
ElevenLabsText to Speech/v1/media/queue

Eleven v3 Conversational API

Eleven v3 Conversational text to speech — Eleven v3 tuned for conversational agents, billed on input length.

A variant of Eleven v3 optimised for natural dialogue in conversational agents. 70+ languages, up to 5,000 characters per request, at half the per-character price of Eleven v3.

Full Docs Get API Key — Free $5 Credit

No credit card required. Takes 30 seconds.

Eleven v3 Conversational API pricing

Pay per request from your YepAPI balance — no subscription, no monthly minimum. Prices updated October 23, 2026.

BillingPrice
Rate$0.0844/1K chars
What it costsPer job
Short reply200 characters$0.017
Blog post narration10,000 characters (~1,600 words)$0.844
Audiobook chapter100,000 characters$8.44

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 v3 Conversational specs

ProviderElevenLabs
Model IDelevenlabs/eleven-v3-conversational
Endpoint/v1/media/queue
TypeText to Speech
Output formatsmp3
Voices21 presets (default sarah)

How to get an Eleven v3 Conversational API key

  1. 1

    Create a free account

    Sign up at yepapi.com with Google or email. It takes about 30 seconds and needs no card.

  2. 2

    Create an API key

    Open the dashboard, go to API Keys and create a key. Copy it — it starts with yep_sk_.

  3. 3

    Call Eleven v3 Conversational

    Send a request to /v1/media/queue with the x-api-key header and model "elevenlabs/eleven-v3-conversational".

  4. 4

    Pay as you go

    Usage is billed per request from your balance. Top up any amount; there is no subscription.

Strengths

✓
Built for dialogue

Optimised for natural back-and-forth in conversational agents.

✓
Eleven v3 lineage

A variant of ElevenLabs' expressive Eleven v3 model.

✓
70+ languages

The same language coverage as Eleven v3.

✓
Half the price of v3

Billed at half of Eleven v3 per character, which matters when every turn is synthesised.

Quick start

Copy this snippet and start making calls with Eleven v3 Conversational.

// 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-v3-conversational",
    "prompt": "Sure, I can help with that. Just so I've got it right — you'd like to move your appointment to next Tuesday?",
    "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 v3 Conversational vs similar models

Every model below runs on the same API key — switch by changing the model ID.

ModelProviderPrice
Eleven v3 ConversationalElevenLabs$0.0844/1K chars
Eleven Flash v2.5ElevenLabs$0.0844/1K chars
Eleven Flash v2ElevenLabs$0.0844/1K chars
Eleven Turbo v2.5ElevenLabs$0.0844/1K chars
Eleven Turbo v2ElevenLabs$0.0844/1K chars
Eleven v4 TurboElevenLabs$0.0844/1K chars
Kokoro 82Mhexgrad$0.0014/1K chars
Fish Audio Drama 3Fish Audio$0.0042/1K chars

Why use Eleven v3 Conversational through YepAPI?

✓One API key for all models — no separate accounts
✓No monthly minimums — pay per call
✓Switch models with one line of code
✓Simple REST API — works from any language
✓Unified billing across all providers
✓No rate limits for most use cases

Eleven v3 Conversational API — natural dialogue for voice agents

Eleven v3 Conversational is a text-to-speech model from ElevenLabs, a variant of Eleven v3 optimised for natural dialogue in conversational agents. It supports more than 70 languages and has a 5,000-character request limit.

On YepAPI it is billed at $0.0844 per 1,000 characters — half the rate of Eleven v3 — through the same media queue as every other speech model.

Start generating in 30 seconds

$5 free credit on signup. No credit card required. Pay per call.

Get API Key

What developers say

“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”

Marcus T.

SEO Platform Founder

“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”

Priya S.

Full-Stack Developer

“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”

Jake R.

Indie Hacker

Frequently asked questions

A variant of Eleven v3 optimised for natural dialogue in conversational agents. 70+ languages, up to 5,000 characters per request, at half the per-character price of Eleven v3.

Eleven v3 Conversational costs $0.0844/1K chars through YepAPI, billed per request with no monthly fee. For example, a short reply (200 characters) costs about $0.017.

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 v3 Conversational and every other model — no separate ElevenLabs account or waitlist.

New YepAPI accounts in most countries get free signup credit, enough to test Eleven v3 Conversational without a card. After that you pay per request at the rates above — there is no subscription.

Use "elevenlabs/eleven-v3-conversational" as the model on /v1/media/queue. The short alias "eleven-v3-conversational" also works.

Ready to use Eleven v3 Conversational?

$5 free credit on signup. No credit card required. Pay per call.

Get API Key — Free $5 Credit Read Docs

Explore more models

Eleven Turbo v2

ElevenLabs

Eleven Turbo v2 text to speech — low-latency English speech, billed on input length.

Per character

Eleven Flash v2

ElevenLabs

Eleven Flash v2 text to speech — ultra-low-latency English speech, billed on input length.

Per character

Eleven Flash v2.5

ElevenLabs

Eleven Flash v2.5 text to speech — ultra-low-latency speech in 32 languages, billed on input length.

Per character

Fish Audio S1

Fish Audio

Fish Audio S1 text to speech — inline emotional control, billed on input length.

Per character

Gemini 3.8 Flash TTS

Google

Gemini 3.8 Flash TTS text to speech — the creative tier of Gemini 3.8 TTS, 30 voices, billed on input length.

Per character

Deepgram Flux TTS

Deepgram

Deepgram Flux TTS text to speech — natural, expressive English across 36 Flux voices, billed on input length.

Per character

More Text to Speech models

All ElevenLabs models →All AI models →