Voice design capabilities offered completely free currently.
这是一种颠覆传统的语音合成方式，它完全摒弃了传统的“选定音色”和“提供音频克隆”的思路，能够做到“无中生有”。
此创新功能作为 MiMo 平台吸引创作者体验的入口产品，现阶段开放全额度限时免费。由于生成特定高质量声音的算力成本较高，建议尽早利用此免费红利期产出内容。
【额外福利】虽然本模型本身免费，如果您还想体验小米的其他付费顶尖模型（如 MiMo V2.5 对话模型），我目前正在使用 MiMo 开放平台，通过我的邀请码注册为新用户，即可获得 $2 API 体验金。 • 邀请码：TUE76X • 注册链接：https://platform.xiaomimimo.com?ref=TUE76X • 兑换方式：注册后点击控制台左下方入口填入，体验金 40 天有效。
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.
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.
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)