Text-to-speech API pricing. Up to 40% below list.

Gemini's text-to-speech models read text aloud in 30 voices. Gemini 3.8 Flash TTS is Google's newest, in more than 130 languages, reading the text word for word with tags such as <laugh> for sounds. Gemini 3.1 Flash TTS is the expressive, steerable one, directed in plain words, in more than 70 languages, where audio tags written into the text change the delivery mid-sentence. Gemini 2.5 Pro TTS is quality-first, for long-form content and narration, and Gemini 2.5 Flash TTS is low-latency and cost-efficient. Zurelay serves them through an OpenAI-compatible speech endpoint, POST /v1/audio/speech.

Text-to-speech models
4
About, per minute
$0.008
Below Google's price
40%
Get your API keySee every price
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="gemini-3.8-flash-tts",
    voice="Kore",
    input="Welcome to Zurelay. Your video is ready, and it looks great.",
)
speech.write_to_file("welcome.mp3")

Pricing

Every text-to-speech model. Live prices, one key.

Each model on Zurelay, with Google's own price beside ours.

Text-to-speech API prices on Zurelay
ModelMakesPriceCompared withYou save
Gemini 3.8 Flash TTSgemini-3.8-flash-ttsSpeech from text
about $0.008
per minute
$0.014
Google list
40%off
Gemini 3.1 Flash TTSgemini-3.1-flash-ttsSpeech from text
about $0.023
per minute
$0.038
Google list
40%off
Gemini 2.5 Pro TTSgemini-2.5-pro-ttsSpeech from text
about $0.018
per minute
$0.03
Google list
40%off
Gemini 2.5 Flash TTSgemini-2.5-flash-ttsSpeech from text
about $0.009
per minute
$0.015
Google list
40%off

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.

Which model

Which model to use. Same key for all of them.

40%off

Newest, in 130+ languages

Gemini 3.8 Flash TTS

$0.30 / $5.40 per 1M tokens

Google's newest speech model, in more than 130 languages, with vocal tags such as <laugh> or <short pause> in the text.

Gemini 3.8 Flash TTS API
40%off

Expressive and steerable

Gemini 3.1 Flash TTS

$0.60 / $12.00 per 1M tokens

Google's steerable speech model, in more than 70 languages, directed in plain words or with audio tags that change the delivery mid-sentence.

Gemini 3.1 Flash TTS API
40%off

Narration and long-form

Gemini 2.5 Pro TTS

$0.60 / $12.00 per 1M tokens

Google's quality-first speech model, built for long-form content and professional narration.

Gemini 2.5 Pro TTS API
40%off

Low latency at volume

Gemini 2.5 Flash TTS

$0.30 / $6.00 per 1M tokens

Google's low-latency, cost-efficient speech model, for assistants, high-volume narration and conversational apps.

Gemini 2.5 Flash TTS API

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.

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="gemini-3.8-flash-tts",
    voice="Kore",
    input="Welcome to Zurelay. Your video is ready, and it looks great.",
)
speech.write_to_file("welcome.mp3")

Verified

The model you asked for. Tested before it serves.

Model capacity is often bought ahead, through prepaid credits, committed-spend contracts and volume tiers, and not all of it gets used. Sellers offer it below the usual price. Zurelay tests each route, pools several per model and sends every request to one that is available and verified.

Failed attempts move to another route, and you aren't billed for them. How models are verified.

Live health for every model is on the status page.

FAQ

Text-to-speech API questions.

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

How much does the text-to-speech API cost?

On Zurelay: Gemini 3.8 Flash TTS $0.30 / $5.40 per 1M tokens; Gemini 3.1 Flash TTS $0.60 / $12.00 per 1M tokens; Gemini 2.5 Pro TTS $0.60 / $12.00 per 1M tokens; Gemini 2.5 Flash TTS $0.30 / $6.00 per 1M tokens. That's 40% below Google's own price. There's no subscription or minimum spend: you add prepaid credit from $10 and pay for what you use.

Are these the real models?

Yes. Each model is served over several routes run by independent sellers, and every route is tested before it serves requests and re-tested while it does. If a result doesn't look right, send its x-request-id to support and we check the route that served it.

How do I start calling these models 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 gemini-3.8-flash-tts, a voice and your text.

How is speech billed?

Per token, as Google bills it: the text you send is input, and the audio you get back is output. A second of speech is 32 audio tokens on Gemini 3.1 Flash TTS and 25 on the others, which is where the price per minute comes from.

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. OpenAI voice names such as alloy and nova map to a Gemini voice that sounds similar.

More pricing

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.

Get your API keyTalk to an engineer