MiMo-V2.5-TTS-VoiceDesign

无需参考音频,一句话描述即可生成全新音色。

多维度语义理解,覆盖口音、年龄、气质与录音质感。

模型规格

模态

输入文本
输出音频

模型能力

音色设计
语音合成
流式输出

性能

上下文长度8K tokens
最大输出8K tokens
RPM100
TPM10M

模型价格

价格
限时免费

模型优势

自然语言生成音色

通过一句自然语言描述即可凭空生成全新音色,无需任何参考音频样本,让音色创作像写一段文字一样直观高效。

多维度音色定制

可从年龄、性别、口音、音色、语速、气质、录音质感等任意维度自由描述,支持从 ASMR 双耳女声到纪录片磁性旁白的跨度极大的音色定义。

复杂模糊描述理解

基于大规模预训练,模型对复杂、模糊甚至矛盾的描述具备良好理解能力,既能还原从未听过的独特音色,也能精准复刻带有鲜明特征的经典人物原型。

多语言多风格覆盖

支持中英文及多种口音的音色设计,中文描述可生成普通话、方言音色,英文描述可生成不同国家口音,语言与风格跨度灵活。

真实任务中的表现

俄罗斯口音中年男性

Instruct

Heavy Russian accent, gruff middle-aged male, blunt and matter-of-fact.

Text

You want my opinion? Fine. This plan will not work. I have seen many plan like this before, all fail. You think you are special? No. You are not. But you never listen, so go, try. When everything fall apart, I will be here, drinking tea. I already told you.

Audio
0:00

ASMR 双耳女声

Instruct

Young female, extreme close-up with a binaural, ear-to-ear ASMR feel. Audible breathing, subtle swallowing, and soft natural lip sounds. She speaks very slowly, creating a deeply relaxing and immersive experience.

Text

[Whispering in your ear] Shhh... just relax, come a little closer. I'm right here beside you now. Breathe slowly and gently, and let your mind drift, as if you're sinking into warm water.

Audio
0:00

纪录片旁白

Instruct

一位中年男性,说标准普通话,嗓音低沉有磁性,带有轻微的沙哑质感,像纪录片旁白解说员,沉稳而有感染力。

Text

当最后一缕阳光消失在地平线之下,这片沉睡了亿万年的大地开始显露它真正的面貌。在这寂静的荒野中,每一块岩石都记录着时间的流逝,每一阵风都在诉说着古老的故事。

Audio
0:00

年迈老先生旁白

Instruct

一位年迈的老先生,说带北方口音的普通话,语速缓慢而沉稳,嗓音略带沙哑和沧桑感,仿佛一位饱经风霜的老爷爷在讲故事,充满岁月的智慧。

Text

我这辈子啊,走南闯北六十多年。见过最热闹的集市,也见过最安静的戈壁。到头来才明白一个道理——这人哪,不在走了多远的路,在于记住了多少风景。年轻人,别光顾着赶路,偶尔也停下来看看天。

Audio
0:00

选择适合你的接入方式

按量计费 API 接入

1

获取 API Key

在控制台创建账号,生成专属 API Key(TTS 系列当前限时免费)。

2

示例代码

通过 messages 传递音色描述和文本内容即可调用。

import os, base64
from openai import OpenAI

client = OpenAI(
    api_key=os.environ.get("MIMO_API_KEY"),
    base_url="https://api.xiaomimimo.com/v1",
)

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voicedesign",
    messages=[
        {"role": "user", "content": "Give me a young male tone."},
        {"role": "assistant", "content": "Yes, I had a sandwich."}
    ],
    audio={"format": "wav", "optimize_text_preview": True}
)

message = completion.choices[0].message
audio_bytes = base64.b64decode(message.audio.data)
with open("audio_file.wav", "wb") as f:
    f.write(audio_bytes)

Token Plan 订阅

1

购买套餐

包月/包年订阅,覆盖 MiMo V2.5 全系模型,高用量场景性价比显著优于按量计费(TTS 系列当前限时免费,不消耗 credits)。

Copyright©2026 Xiaomi. All Rights Reserved | Cookie Policy | Cookie Preferences

We use cookies and similar technologies of our own to ensure the proper functioning of the website, customize content according to user preferences and analyze users' interactions on the website, as well as their browsing habits. You can find more information in our Cookie Policy. Select an option or go to Cookie Settings to manage your preferences. Learn More.