MiMo-V2.5-TTS-VoiceDesign
Generate any voice from a text description alone — no reference audio needed.
Multi-dimensional customization across accent, age, timbre, and recording texture.
Model Specs
Modality
Capabilities
Performance
Model Pricing
Model Advantages
Voice Generation from Text
Describe a voice in natural language and the model generates it from scratch — no reference audio required.
Multi-Dimensional Customization
Describe from any angle: age, gender, accent, timbre, pacing, temperament, or recording texture — the full spectrum without specialized audio knowledge.
Complex Description Handling
Strong comprehension of complex, ambiguous, or layered descriptions. Handles both unique unheard voices and precise reproductions of classic character archetypes.
Multi-Language Coverage
Voice design works across Chinese, English, and varied accents — Mandarin or dialect voices, different national accents, and more — with flexible range across languages and styles.
Real-World Performance
Russian Accent
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.
Binaural ASMR
Instruct
Young female, extreme close-up with a binaural, ear-to-ear ASMR feel.
Text
[Whispering] Shhh... just relax, come a little closer. I'm right here beside you now.
Documentary Narrator
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。
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。
Elderly Narrator
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。
Text
我这辈子啊，走南闯北六十多年。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。
Choose Your Access Method
Pay-As-You-Go API
Sample Code
Pass a voice description and text content via messages.
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 Subscription
Subscribe
Monthly or annual plans covering mimo-v2.6-pro, mimo-v2.6-flash and the full MiMo V2.5 model suite — significantly better value than pay-as-you-go at high usage volumes.
Get Token Plan API Key
After subscribing, generate a dedicated API key from the Token Plan page — separate from your pay-as-you-go key.
Quick Integration
Same API format as pay-as-you-go — just swap the key and base URL. Works directly with Claude Code, Cline, and other popular AI tools.
Use in MiMo Claw
MiMo Claw is equipped with MiMo's latest flagship model, and supports both the latest multimodal understanding and voice series large language models. It can be added with one click for subscription across all tiers of TokenPlan, and is currently available for a limited-time free trial.