Expressive voice generation

ElevenLabs v3 API

ElevenLabs most expressive multilingual speech model.

ElevenLabs v3 is a text-to-speech model from ElevenLabs, available on OttoPort's OpenAI-compatible API as the model ID eleven-v3 at $103.50 / 1M characters as of 2026-10-14.

Provider

ElevenLabs

Price

$103.50 / 1M characters

Model ID

eleven-v3

Type

text-to-speech model

NarrationCharacter voiceGlobal audio

Create with ElevenLabs v3

tts

ScriptVoice (optional)

Your result appears here

Start with the example prompt or make it your own. Your OttoPort account is used securely for generation.

Pricing

ElevenLabs v3 API pricing

What OttoPort bills for ElevenLabs v3, and what that works out to per unit. Rates are read from the same catalog the gateway meters against, and were current on 2026-10-14.

Per 1M characters	$103.50
1,000 characters	$0.1035	roughly 150 spoken words
A 500-word script	$0.2846	about 2,750 characters
Characters per $1	9,661

No subscription and no minimum — OttoPort bills prepaid credits against usage. See the full rate card.

Quickstart

Call ElevenLabs v3 in three lines

Send "model": "eleven-v3" to POST https://ottoport.ai/api/v1/audio/speech with an OttoPort key. No ElevenLabs account, no waitlist, no separate SDK.

curl https://ottoport.ai/api/v1/audio/speech \
  -H "Authorization: Bearer $OTTOPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "eleven-v3",
    "input": "Welcome to OttoPort.",
    "format": "mp3"
  }' --output speech.mp3

import requests

audio = requests.post(
    "https://ottoport.ai/api/v1/audio/speech",
    headers={"Authorization": "Bearer " + API_KEY},
    json={"model": "eleven-v3", "input": "Welcome to OttoPort.", "format": "mp3"},
)
open("speech.mp3", "wb").write(audio.content)

const res = await fetch("https://ottoport.ai/api/v1/audio/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "eleven-v3",
    input: "Welcome to OttoPort.",
    format: "mp3",
  }),
});
const buffer = Buffer.from(await res.arrayBuffer());

Before you start

1. Create a key at /api-keys.
2. Top up credits — the smallest pack is $25.
3. Paste the request. It returns on the same request.

Full reference at /docs, or drive it from an agent with the MCP server and CLI.

Reference

Request parameters

The body POST https://ottoport.ai/api/v1/audio/speech accepts for ElevenLabs v3.

Field	Type	Required	Notes
model	string	Yes	Always eleven-v3 for ElevenLabs v3.
input	string	Yes	Text to speak. Characters are the billed unit.
voice	string	No	Provider voice identifier.
format	string	No	Audio container, e.g. `mp3`.

Comparison

ElevenLabs v3 direct vs through OttoPort

ElevenLabs v3 is the same model either way — what changes is how many accounts, keys, and integrations you carry to reach it.

	ElevenLabs direct	Via OttoPort
Accounts and keys	An ElevenLabs account, plus one more for every other model you add	One OttoPort account and one key for the whole catalog
Request shape	ElevenLabs's own SDK and response format	OpenAI-compatible — point baseURL at OttoPort and change the model string
Switching models	A new integration per provider	Replace eleven-v3 with any other model ID in the catalog
Billing	A separate invoice and contract per provider	Prepaid credits, no subscription, one usage ledger
Provider outages	Your call fails	Configured backup routes are tried in order on provider failure

Write for the ear, not the page.

Use punctuation to guide pauses.

Keep each generation focused on one tone.

FAQ

ElevenLabs v3 API questions

Cost, keys, and model IDs for ElevenLabs v3 on OttoPort.

How much does the ElevenLabs v3 API cost?

On OttoPort, ElevenLabs v3 costs $103.50 / 1M characters as of 2026-10-14. For scale, a 500-word script: $0.2846. Billing is prepaid usage with no subscription and no minimum, and the current rate is always published at ottoport.ai/pricing.

How do I get an ElevenLabs v3 API key?

You do not need an ElevenLabs key. Create an OttoPort account, generate a key at ottoport.ai/api-keys, and send it as "Authorization: Bearer <key>" to POST https://ottoport.ai/api/v1/audio/speech with "model": "eleven-v3". The same key reaches every other model in the catalog.

What is the model ID for ElevenLabs v3?

The OttoPort model ID for ElevenLabs v3 is eleven-v3. Pass it as the model field on POST https://ottoport.ai/api/v1/audio/speech, or list it programmatically from GET https://ottoport.ai/api/v1/models.

Do I need an ElevenLabs account to use ElevenLabs v3?

No. OttoPort connects to ElevenLabs on your behalf, so one OttoPort account covers ElevenLabs v3 and every other model in the catalog — no per-provider contracts, keys, or invoices.

Alternatives

Other text-to-speech models on the same API

Same endpoint, same key — swapping model is a one-string change from eleven-v3.

MiniMax Speech 2.8 Turbo API

MiniMax

$72.79 / 1M characters

MiniMax Speech 2.8 HD API

MiniMax

$121.32 / 1M characters

Seed Audio 1.0 API

ByteDance

$0.329 / request

Gemini 2.5 Flash TTS API

Google

$11.50 / 1M characters

GPT-4o mini TTS API

OpenAI

$13.80 / 1M characters

ElevenLabs Turbo 2.5 API

ElevenLabs

$51.75 / 1M characters

Browse the full catalog — every model with its provider and per-unit price.