Free Mimo TTS 2.5 (Voice Design) on Xiaomi

Voice design capabilities offered completely free currently.

Updated 5/11/20261 code examples

About the Model

Why choose MIMO Voice Design 2.5?

This is a way of subverting the traditional speech synthesis. It completely abandons the traditional "selected sound" and "providing audio clones", and it can "create something out of nothing".

Core strengths and characteristics

Natural language kneading voice: You only need to enter a text description similar to "Rough, a little middle-aged uncle with a little accent", and the big model can directly generate a unique voice in the world according to semantic understanding.
Director mode control: It supports to control the background of the characters, the current scene, and even a specific interpretation style through prompt words, which provides endless imagination space for content creation.
Zero-sample requirements: You don't even need to prepare clean audio for dozens of seconds, completely breaking the material limit.

View all free providers for Mimo TTS 2.5 (Voice Design)

How to Access for Free (via Xiaomi)

Free basis (Why is it free?)

This innovative function is an entrance product that attracts creators to experience the MIMO platform, and is now open for a limited time and free. Due to the high computing power cost of generating specific high-quality sounds, it is recommended to use this free bonus period to produce content as soon as possible.

[Additional benefits] Although this model itself is free, if you also want to experience other paid top models of Xiaomi (such as MIMO V2.5 dialogue model), I am currently using the MIMO open platform, register as a new user through my invitation code, you can get the $2 API Experience gold. • Invitation code: tue76x • Registration link: https://platform.xiaomimimo.com?ref=tue76x • Exchange method: Click the entrance to the lower left of the console to fill in after registration, and the experience bonus Valid for 40 days.

📖 View Full Guide

Try it in your browser

Pick a model, paste your own free key, and run. Your key is sent once to call the provider and never stored on our servers.

Code Examples

python

import os
from openai import OpenAI
import base64

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": "A deep, gravelly middle-aged male voice with a heavy accent, sounding blunt and matter-of-fact."
        },
        {
            "role": "assistant", 
            "content": "I don't have time for games. Tell me what you know, or leave."
        }
    ],
    audio={ "format": "wav" }
)

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