ElevenLabs API pricing. From about $0.043 a minute.

ElevenLabs makes text-to-speech models known for lifelike, expressive voices. Eleven v4 is its most emotive model, for narration and characters, and Eleven v4 Turbo is the fast one for voice agents. Eleven v3 is the earlier expressive model, Eleven Multilingual v2 the steadiest on long text, and Eleven Flash v2.5 the quickest. On Zurelay they run through OpenAI's speech API with 17 ElevenLabs voices, priced by the character of text, on the same key as every other model.

ElevenLabs models
5
About, per minute
$0.043
Charged
On delivery
speak.py
from openai import OpenAI
client = OpenAI(
base_url="https://api.zurelay.com/v1",
api_key="YOUR_ZURELAY_KEY",
)
speech = client.audio.speech.create(
model="eleven-v4",
voice="Talia",
input="Welcome to Zurelay. Your video is ready.",
)
speech.write_to_file("welcome.mp3")

Pricing

Every ElevenLabs model. Live prices, one key.

Each model's price on Zurelay, live from the catalog.

ElevenLabs API prices on Zurelay
ModelMakesPriceCompared withYou save
Eleven v4eleven-v4Speech from text
about $0.085
per minute
——
Eleven v4 Turboeleven-v4-turboSpeech from text
about $0.043
per minute
——
Eleven v3eleven-v3Speech from text
about $0.085
per minute
——
Eleven Multilingual v2eleven-multilingual-v2Speech from text
about $0.085
per minute
——
Eleven Flash v2.5eleven-flash-v2.5Speech from text
about $0.043
per minute
——

Prices in US dollars, live from the catalog. Speech is compared with the lab's list price, worked out per minute. Each model's own page has every price it charges.

Quickstart

One request. OpenAI's format.

Point the OpenAI SDK at https://api.zurelay.com/v1 and call audio.speech.create with a voice and your text. Voices, styles and formats are in the speech guide.

Add credit from $10, with no subscription. The quickstart has the rest, and every ElevenLabs model has its own page.

speak.py
from openai import OpenAI
client = OpenAI(
base_url="https://api.zurelay.com/v1",
api_key="YOUR_ZURELAY_KEY",
)
speech = client.audio.speech.create(
model="eleven-v4",
voice="Talia",
input="Welcome to Zurelay. Your video is ready.",
)
speech.write_to_file("welcome.mp3")

Verified

The ElevenLabs you asked for. ElevenLabs' own API.

These models run on ElevenLabs' own API, under the model IDs ElevenLabs gives them, so the voice you hear is ElevenLabs'. Zurelay doesn't swap in a different or smaller model.

Each model was tested through Zurelay before launch: every voice name, MP3, WAV and PCM output, and the characters billed against the characters sent. Requests that fail cost nothing.

Live health for every model is on the status page.

FAQ

ElevenLabs API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the ElevenLabs API cost?

On Zurelay: Eleven v4 $0.10 per 1K characters; Eleven v4 Turbo $0.05 per 1K characters; Eleven v3 $0.10 per 1K characters; Eleven Multilingual v2 $0.10 per 1K characters; Eleven Flash v2.5 $0.05 per 1K characters. There's no subscription or minimum spend: you add prepaid credit from $10 and pay for what you use.

How do I start calling ElevenLabs through Zurelay?

Create a key, then call audio.speech.create in the OpenAI SDK at https://api.zurelay.com/v1 with a model ID such as eleven-v4, a voice and your text.

Is it the real ElevenLabs?

Yes. Requests run on ElevenLabs' own API, under ElevenLabs' model IDs, and Zurelay doesn't swap in a different model. Zurelay is an independent service and is not affiliated with ElevenLabs.

How is ElevenLabs speech billed on Zurelay?

By the character of text you send, spaces and punctuation included, with the audio included. A minute of speech is about 850 characters. ElevenLabs' own API costs less per character; on Zurelay you get it on the same key and prepaid balance as every other model, with no ElevenLabs subscription.

Which ElevenLabs voices are there?

17: Talia, Elara, Baxter, Eldrin, Elowen, Kaelen, Lawrence, Alicia, Maisie, Warren, Jade, Eddie, Caleb, Sawyer, Finley, Florence and Darian. OpenAI voice names such as alloy and nova work too. Voice cloning and ElevenLabs' voice library aren't available through Zurelay.

Does it work with OpenAI's speech API?

Yes. Call audio.speech.create with the model ID, a voice and your text, with the base URL set to https://api.zurelay.com/v1. The reply is an MP3, or WAV or PCM if you ask.

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.