Text-to-speech API 价格。 最多 40% below list. 个

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 和 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 模型
4
约合,每分钟
$0.008
低于 Google's price
40%
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")

价格

所有 text-to-speech 模型。 实时价格,一个 API key。

Zurelay 上的各款模型,与 Google's 的官方价格并排对比。

Zurelay 上的 Text-to-speech API 价格
模型生成内容价格对比价格节省金额
Gemini 3.8 Flash TTSgemini-3.8-flash-tts文本转语音
约 $0.008
每分钟
$0.014
Google 原价
40%优惠
Gemini 3.1 Flash TTSgemini-3.1-flash-tts文本转语音
约 $0.023
每分钟
$0.038
Google 原价
40%优惠
Gemini 2.5 Pro TTSgemini-2.5-pro-tts文本转语音
约 $0.018
每分钟
$0.03
Google 原价
40%优惠
Gemini 2.5 Flash TTSgemini-2.5-flash-tts文本转语音
约 $0.009
每分钟
$0.015
Google 原价
40%优惠

价格以美元计,实时取自模型目录。Speech is compared with the lab's list price, worked out per minute. 各模型页面列有完整的计费价格。

快速开始

一次请求。 OpenAI 格式。

将 OpenAI SDK 指向 https://api.zurelay.com/v1, 然后调用 audio.speech.create, 指定音色并传入文本。音色、风格和格式详见语音指南。

$10 起充值,无需订阅。其余步骤详见快速入门。

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")

已验证

你指定的模型。 先测试,再提供服务。

模型用量通常通过预付额度、消费承诺合约和阶梯批量定价提前购买,但未必全部用完。卖家会以低于常规价格的价格出售剩余用量。Zurelay 会测试每条接入渠道,为每款模型汇集多条渠道,并将每次请求发送到可用且已通过验证的渠道。

尝试失败后,请求会转至其他渠道,失败尝试不计费。 模型如何验证.

各模型的实时运行状况可在状态页查看。

常见问题

Text-to-speech API 常见问题。

还有其他问题?联系我们的团队,我们会通过邮件回复。

text-to-speech API 如何收费?

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 和 pay for what you use.

这些都是原版模型吗?

Yes. Each model is served over several routes run by independent sellers, 和 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.

如何通过 Zurelay 开始调用这些模型?

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 和 your text.

语音如何计费?

与 Google 一样,按 token 计费:发送的文本算输入,返回的音频算输出。Gemini 3.1 Flash TTS 每秒语音对应 32 个音频 token,其他模型则为 25 个,每分钟价格据此换算。

兼容 OpenAI 的语音 API 吗?

兼容。将基础 URL 设为 https://api.zurelay.com/v1,然后调用 audio.speech.create,传入模型 ID、音色和文本即可。alloy、nova 等 OpenAI 音色名称会映射到听感相近的 Gemini 音色。

告别原价.
今天就开始省钱.

几秒钟即可创建密钥,将你正在使用的 SDK 指向 Zurelay,从第一个 token 起,每次请求的费用最高可省 90%。