语音合成（MiMo-V2.5-TTS 系列）

角色：百年门阀岑家的现任大当家。自出生便被过继给祖庙的守门老人抚养，被塑造成一尊完美无瑕、绝情断欲的家族图腾。常年深居简出，对人有着极强的阶级疏离感。

场景：在祠堂的阴影里，看着那个不顾一切冲破保安防线来找她、企图带她私奔的男人。她要用最冷硬的阶级壁垒，绞杀对方，也绞杀自己刚刚萌芽、却足以燎原的感情。

指导：
冰冷、慵懒却极具威压的低音御姐。发声通道非常松弛，没有任何剑拔弩张，却有着让人骨里生寒的压迫感。

- 语速与顿挫：极慢，每个字都像是在舌尖滚过才吐出来，带着上位者漫不经心的傲慢。句与句之间留下极长的、令人不安的空白。
- 气声与实声：大部分时间，她的声音没有明显的声调起伏，实音重且硬，像是一条平缓却冰冷的暗河。但一定要在某些尾音处（如“真心”），加入极其轻微的气音收束，透出一丝连她自己都没察觉到的疲惫与渴望。
- 咬字肌理：文白杂糅的用词带着旧时代的痕迹，唇齿音发得极轻但极清晰（如“冲撞”“廉价”），显得既清雅又锋利，刀刀见血。

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts",
    "messages": [
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you are bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    "audio": {
        "format": "wav",
        "voice": "Chloe"
    }
}'

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",
    messages=[
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you're bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    audio={
        "format": "wav",
        "voice": "Chloe"
    }
)

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

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts",
    "messages": [
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you are bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    "audio": {
        "format": "pcm16",
        "voice": "Chloe"
    },
    "stream": true
}'

import base64
import os
import numpy as np
import soundfile as sf
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",
    messages=[
        {
            "role": "user",
            "content": "Bright, bouncy, slightly sing-song tone — like you're bursting with good news you can barely hold in. Fast pace, rising pitch at the end."
        },
        {
            "role": "assistant",
            "content": "Hey boss — guess what, guess what? I just got the results back and I actually passed! Not just passed, I got a distinction! I know, I know — you told me I was cutting it close, but hey, here we are. Drinks are on me tonight, okay?"
        }
    ],
    audio={
        "format": "pcm16",
        "voice": "Chloe"
    },
    stream=True
)

# 24kHz PCM16LE mono audio
collected_chunks: np.ndarray = np.array([], dtype=np.float32)

for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    audio = getattr(delta, "audio", None)

    if audio is not None:
        assert isinstance(audio, dict), f"Expected audio to be a dict, got {type(audio)}"
        pcm_bytes = base64.b64decode(audio["data"])
        np_pcm = np.frombuffer(pcm_bytes, dtype=np.int16).astype(np.float32) / 32768.0
        collected_chunks = np.concatenate((collected_chunks, np_pcm))
        print(f"Received audio chunk of size {len(pcm_bytes)} bytes")

# Save the collected audio to a file
os.makedirs("tmp", exist_ok=True)
sf.write("tmp/output.wav", collected_chunks, samplerate=24000)
print("Audio saved to tmp/output.wav")

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

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.

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。

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "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
    }
}'

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": "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)

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts-voicedesign",
    "messages": [
        {
            "role": "user",
            "content": "Give me a young male tone."
        },
        {
            "role": "assistant",
            "content": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    "audio": {
        "format": "pcm16",
        "optimize_text_preview": true
    },
    "stream": true
}'

import base64
import os
import numpy as np
import soundfile as sf
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": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    audio={
        "format": "pcm16",
        "optimize_text_preview": True
    },
    stream=True
)

# 24kHz PCM16LE mono audio
collected_chunks: np.ndarray = np.array([], dtype=np.float32)

for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    audio = getattr(delta, "audio", None)

    if audio is not None:
        assert isinstance(audio, dict), f"Expected audio to be a dict, got {type(audio)}"
        pcm_bytes = base64.b64decode(audio["data"])
        np_pcm = np.frombuffer(pcm_bytes, dtype=np.int16).astype(np.float32) / 32768.0
        collected_chunks = np.concatenate((collected_chunks, np_pcm))
        print(f"Received audio chunk of size {len(pcm_bytes)} bytes")

# Save the collected audio to a file
os.makedirs("tmp", exist_ok=True)
sf.write("tmp/output.wav", collected_chunks, samplerate=24000)
print("Audio saved to tmp/output.wav")

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts-voiceclone",
    "messages": [
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant",
            "content": "Yes, I had a sandwich."
        }
    ],
    "audio": {
        "format": "wav",
        "voice": "data:{MIME_TYPE};base64,$BASE64_AUDIO"
    }
}'

import base64
import os

from openai import OpenAI

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

with open("voice.mp3", "rb") as f:
    voice_bytes = f.read()
voice_base64 = base64.b64encode(voice_bytes).decode("utf-8")

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voiceclone",
    messages=[
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant", 
            "content": "Yes, I had a sandwich."
        }
    ],
    audio={
        "format": "wav",
        "voice": f"data:audio/mpeg;base64,{voice_base64}"
    }
)

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

curl --location --request POST 'https://api.xiaomimimo.com/v1/chat/completions' \
--header "api-key: $MIMO_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
    "model": "mimo-v2.5-tts-voiceclone",
    "messages": [
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant",
            "content": "You are UN-BE-LIEVABLE! I am sooooo done with your constant lies. GET. OUT!"
        }
    ],
    "audio": {
        "format": "pcm16",
        "voice": "data:{MIME_TYPE};base64,$BASE64_AUDIO"
    },
    "stream": true
}'

import base64
import os

import numpy as np
import soundfile as sf
from openai import OpenAI

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

with open("voice.mp3", "rb") as f:
    voice_bytes = f.read()
voice_base64 = base64.b64encode(voice_bytes).decode("utf-8")

completion = client.chat.completions.create(
    model="mimo-v2.5-tts-voiceclone",
    messages=[
        {
            "role": "user",
            "content": ""
        },
        {
            "role": "assistant", 
            "content": "Yes, I had a sandwich."
        }
    ],
    audio={
        "format": "wav",
        "voice": f"data:audio/mpeg;base64,{voice_base64}",
    },
    stream=True
)

# 24kHz PCM16LE mono audio
collected_chunks: np.ndarray = np.array([], dtype=np.float32)

for chunk in completion:
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    audio = getattr(delta, "audio", None)

    if audio is not None:
        assert isinstance(audio, dict), (
            f"Expected audio to be a dict, got {type(audio)}"
        )
        pcm_bytes = base64.b64decode(audio["data"])
        np_pcm = np.frombuffer(pcm_bytes, dtype=np.int16).astype(np.float32) / 32768.0
        collected_chunks = np.concatenate((collected_chunks, np_pcm))
        print(f"Received audio chunk of size {len(pcm_bytes)} bytes")

# Save the collected audio to a file
os.makedirs("tmp", exist_ok=True)
sf.write("tmp/output.wav", collected_chunks, samplerate=24000)
print("Audio saved to tmp/output.wav")