Convert half-duplex model to duplex mode

Image Understanding (Instruct)

Image Understanding (Thinking)

Video Understanding

OmniDocBench

Text Capability

Omni Half-Duplex

Vision Duplex

Audio Understanding

Speech Generation

Long Speech Generation

Emotion Control

Inference Efficiency

Note: FFmpeg is required for video frame extraction (get_video_frame_audio_segments with use_ffmpeg=True) and video generation (generate_duplex_video). For more information, visit the official FFmpeg website.

macOS (Homebrew):

brew install ffmpeg

Ubuntu/Debian:

sudo apt update && sudo apt install ffmpeg

Verify installation:

ffmpeg -version

import torch
from transformers import AutoModel

# Load omni model (default: init_vision=True, init_audio=True, init_tts=True)
# For vision-only model: set init_audio=False and init_tts=False
# For audio-only model: set init_vision=False
model = AutoModel.from_pretrained(
    "openbmb/MiniCPM-o-4_5",
    trust_remote_code=True,
    attn_implementation="sdpa", # sdpa or flash_attention_2
    torch_dtype=torch.bfloat16,
    init_vision=True,
    init_audio=True,
    init_tts=True,
)
model.eval().cuda()

# Initialize TTS for audio output
model.init_tts()

# Convert half-duplex model to duplex mode
duplex_model = model.as_duplex()

# Convert duplex model back to half-duplex mode
model = duplex_model.as_simplex(reset_session=True)

import librosa
import torch
from minicpmo.utils import generate_duplex_video, get_video_frame_audio_segments
from transformers import AutoModel

# Load model and convert to duplex mode
model = AutoModel.from_pretrained(
    "openbmb/MiniCPM-o-4_5",
    trust_remote_code=True,
    attn_implementation="sdpa",  # or "flash_attention_2"
    torch_dtype=torch.bfloat16,
)
model.eval().cuda()
model = model.as_duplex()

# Load video and reference audio
video_path = "assets/omni_duplex1.mp4"
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)

# Extract video frames and audio segments
video_frames, audio_segments, stacked_frames = get_video_frame_audio_segments(
    video_path, stack_frames=1, use_ffmpeg=True, adjust_audio_length=True
)

# Prepare duplex session with system prompt and voice reference
model.prepare(
    prefix_system_prompt="Streaming Omni Conversation.",
    ref_audio=ref_audio,
    prompt_wav_path=ref_audio_path,
)

results_log = []
timed_output_audio = []

# Process each chunk in streaming fashion
for chunk_idx in range(len(audio_segments)):
    audio_chunk = audio_segments[chunk_idx] if chunk_idx < len(audio_segments) else None
    frame = video_frames[chunk_idx] if chunk_idx < len(video_frames) else None
    frame_list = []
    if frame is not None:
        frame_list.append(frame)
        if stacked_frames is not None and chunk_idx < len(stacked_frames) and stacked_frames[chunk_idx] is not None:
            frame_list.append(stacked_frames[chunk_idx])

    # Step 1: Streaming prefill
    model.streaming_prefill(
        audio_waveform=audio_chunk,
        frame_list=frame_list,
        max_slice_nums=1,  # Increase for HD mode (e.g., [2, 1] for stacked frames)
        batch_vision_feed=False,  # Set True for faster processing
    )

    # Step 2: Streaming generate
    result = model.streaming_generate(
        prompt_wav_path=ref_audio_path,
        max_new_speak_tokens_per_chunk=20,
        decode_mode="sampling",
    )

    if result["audio_waveform"] is not None:
        timed_output_audio.append((chunk_idx, result["audio_waveform"]))

    chunk_result = {
        "chunk_idx": chunk_idx,
        "is_listen": result["is_listen"],
        "text": result["text"],
        "end_of_turn": result["end_of_turn"],
        "current_time": result["current_time"],
        "audio_length": len(result["audio_waveform"]) if result["audio_waveform"] is not None else 0,
    }
    results_log.append(chunk_result)
    
    print("listen..." if result["is_listen"] else f"speak> {result['text']}")

# Generate output video with AI responses
# Please install Chinese fonts (fonts-noto-cjk or fonts-wqy-microhei) to render CJK subtitles correctly.
# apt-get install -y fonts-noto-cjk fonts-wqy-microhei
# fc-cache -fv
generate_duplex_video(
    video_path=video_path,
    output_video_path="duplex_output.mp4",
    results_log=results_log,
    timed_output_audio=timed_output_audio,
    output_sample_rate=24000,
)

from minicpmo.utils import get_video_frame_audio_segments

model = ...
model.init_tts()

video_path = "assets/Skiing.mp4"

# Optional: Set reference audio for voice cloning
ref_audio_path = "assets/HT_ref_audio.wav"
sys_msg = model.get_sys_prompt(ref_audio=ref_audio_path, mode="omni", language="en")

# Use stack_frames=5 for high refresh rate mode
video_frames, audio_segments, stacked_frames = get_video_frame_audio_segments(video_path, stack_frames=1)
omni_contents = []
for i in range(len(video_frames)):
    omni_contents.append(video_frames[i])
    omni_contents.append(audio_segments[i])
    if stacked_frames is not None and stacked_frames[i] is not None:
        omni_contents.append(stacked_frames[i])

msg = {"role": "user", "content": omni_contents}
msgs = [sys_msg, msg]

# Set generate_audio=True and output_audio_path to save TTS output
generate_audio = True
output_audio_path = "output.wav"

res = model.chat(
    msgs=msgs,
    max_new_tokens=4096,
    do_sample=True,
    temperature=0.7,
    use_tts_template=True,
    enable_thinking=False,
    omni_mode=True,  # Required for omni inference
    generate_audio=generate_audio,
    output_audio_path=output_audio_path,
    max_slice_nums=1,  # Increase for HD mode
)
print(res)

# Example output: "The person in the picture is skiing down a snowy mountain slope."
# import IPython
# IPython.display.Audio("output.wav")

import librosa
import numpy as np
import soundfile as sf
import torch
from minicpmo.utils import get_video_frame_audio_segments

model = ...
model.init_tts()

# Reset session for a new conversation (clears KV cache)
model.reset_session()

# Optional: Load reference audio for voice cloning
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
model.init_token2wav_cache(ref_audio)

session_id = "demo"

# Extract video frames and audio segments (use stack_frames=5 for high refresh rate mode)
video_path = "assets/Skiing.mp4"
video_frames, audio_segments, stacked_frames = get_video_frame_audio_segments(video_path, stack_frames=1)

# Build omni contents list
omni_contents = []
for i in range(len(video_frames)):
    omni_contents.append(video_frames[i])
    omni_contents.append(audio_segments[i])
    if stacked_frames is not None and stacked_frames[i] is not None:
        omni_contents.append(stacked_frames[i])

generate_audio = False
output_audio_path = "output.wav"

# Step 1: Prefill system prompt
sys_msg = model.get_sys_prompt(ref_audio=ref_audio, mode="omni", language="en")
model.streaming_prefill(session_id=session_id, msgs=[sys_msg])

# Step 2: Prefill omni chunks (is_last_chunk=True only for the last audio chunk)
audio_indices = [i for i, c in enumerate(omni_contents) if isinstance(c, np.ndarray)]
last_audio_idx = audio_indices[-1] if audio_indices else -1

for idx, content in enumerate(omni_contents):
    is_last_audio_chunk = idx == last_audio_idx
    msgs = [{"role": "user", "content": [content]}]
    model.streaming_prefill(session_id=session_id, msgs=msgs, omni_mode=True, is_last_chunk=is_last_audio_chunk)

# Step 3: Generate response
iter_gen = model.streaming_generate(
    session_id=session_id,
    generate_audio=generate_audio,
    use_tts_template=True,
    enable_thinking=False,
    do_sample=True,
)

audios = []
text = ""

if generate_audio:
    for wav_chunk, text_chunk in iter_gen:
        audios.append(wav_chunk)
        text += text_chunk

    generated_waveform = torch.cat(audios, dim=-1)[0]
    sf.write(output_audio_path, generated_waveform.cpu().numpy(), samplerate=24000)

    print("Text:", text)
    print("Audio saved to output.wav")
else:
    for text_chunk, is_finished in iter_gen:
        text += text_chunk
    print("Text:", text)

First, make sure you have all dependencies, especially "minicpmo-utils[all]>=1.0.5":

pip install "transformers==4.51.0" accelerate "torch>=2.3.0,<=2.8.0" "torchaudio<=2.8.0" "minicpmo-utils[all]>=1.0.5"

import librosa
import numpy as np
import torch
import soundfile as sf

model = ...

# Set reference audio for voice style
ref_audio_path = "ref_audio_path"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)

# Example system msg for English Conversation
sys_msg = {
  "role": "system",
  "content": [
    "Clone the voice in the provided audio prompt.",
    ref_audio,
    "Please assist users while maintaining this voice style. Please answer the user's questions seriously and in a high quality. Please chat with the user in a highly human-like and oral style. You are a helpful assistant developed by ModelBest: MiniCPM-Omni"
  ]
}

# Example system msg for Chinese Conversation
sys_msg = {
  "role": "system",
  "content": [
    "模仿输入音频中的声音特征。",
    ref_audio,
    "你的任务是用这种声音模式来当一个助手。请认真、高质量地回复用户的问题。请用高自然度的方式和用户聊天。你是由面壁智能开发的人工智能助手：面壁小钢炮。"
  ]
}

# You can use each type of system prompt mentioned above in streaming speech conversation

# Reset state
model.init_tts()
model.reset_session(reset_token2wav_cache=True)
model.init_token2wav_cache(prompt_speech_16k=ref_audio)

session_id = "demo"

# First, prefill system turn
model.streaming_prefill(
    session_id=session_id,
    msgs=[sys_msg],
    omni_mode=False,
    is_last_chunk=True,
)

# Here we simulate realtime speech conversation by splitting whole user input audio into chunks of 1s.
user_audio, _ = librosa.load("user_audio.wav", sr=16000, mono=True)

IN_SAMPLE_RATE = 16000 # input audio sample rate, fixed value
CHUNK_SAMPLES = IN_SAMPLE_RATE # sample
OUT_SAMPLE_RATE = 24000 # output audio sample rate, fixed value
MIN_AUDIO_SAMPLES = 16000

total_samples = len(user_audio)
num_chunks = (total_samples + CHUNK_SAMPLES - 1) // CHUNK_SAMPLES

for chunk_idx in range(num_chunks):
    start = chunk_idx * CHUNK_SAMPLES
    end = min((chunk_idx + 1) * CHUNK_SAMPLES, total_samples)
    chunk_audio = user_audio[start:end]
    
    is_last_chunk = (chunk_idx == num_chunks - 1)
    if is_last_chunk and len(chunk_audio) < MIN_AUDIO_SAMPLES:
        chunk_audio = np.concatenate([chunk_audio, np.zeros(MIN_AUDIO_SAMPLES - len(chunk_audio), dtype=chunk_audio.dtype)])

    user_msg = {"role": "user", "content": [chunk_audio]}
    
    # For each 1s audio chunk, perform streaming_prefill once to reduce first-token latency
    model.streaming_prefill(
        session_id=session_id,
        msgs=[user_msg],
        omni_mode=False,
        is_last_chunk=is_last_chunk,
    )


# Let model generate response in a streaming manner
generate_audio = True
iter_gen = model.streaming_generate(
    session_id=session_id,
    generate_audio=generate_audio,
    use_tts_template=True,
    enable_thinking=False,
    do_sample=True,
    max_new_tokens=512,
    length_penalty=1.1, # For realtime speech conversation mode, we suggest length_penalty=1.1 to improve response content
)

audios = []
text = ""

output_audio_path = ...
if generate_audio:
    for wav_chunk, text_chunk in iter_gen:
        audios.append(wav_chunk)
        text += text_chunk

    generated_waveform = torch.cat(audios, dim=-1)[0]
    sf.write(output_audio_path, generated_waveform.cpu().numpy(), samplerate=24000)

    print("Text:", text)
    print("Audio saved to output.wav")
else:
    for text_chunk, is_finished in iter_gen:
        text += text_chunk
    print("Text:", text)

# Now we can prefill the following user turns and generate next turn response...

Built on carefully designed post-training data and professional voice-actor recordings, MiniCPM-o-4.5 can also function as an AI voice assistant. It delivers high-quality spoken interaction out of the box. It produces a sweet and expressive voice with natural prosody, including appropriate rhythm, stress, and pauses, giving a strong sense of liveliness in casual conversation. It also supports storytelling and narrative speech with coherent and engaging delivery. Moreover, it enables advanced voice instruction control. like emotional tone, word-level emphasis.

import librosa

# Set reference audio for voice style
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)

# For Chinese Conversation
sys_msg = {
  "role": "system",
  "content": [
    "模仿输入音频中的声音特征。",
    ref_audio,
    "你的任务是用这种声音模式来当一个助手。请认真、高质量地回复用户的问题。请用高自然度的方式和用户聊天。你是由面壁智能开发的人工智能助手：面壁小钢炮。"
  ]
}

# For English Conversation
sys_msg = {
  "role": "system",
  "content": [
    "Clone the voice in the provided audio prompt.",
    ref_audio,
    "Please assist users while maintaining this voice style. Please answer the user's questions seriously and in a high quality. Please chat with the user in a highly human-like and oral style. You are a helpful assistant developed by ModelBest: MiniCPM-Omni."
  ]
}

MiniCPM-o-4.5 can role-play as a specific character based on an audio prompt and text profile prompt. It mimics the character's voice and adopts their language style in text responses. It also follows profile defined in text profile. In this mode, MiniCPM-o-4.5 sounds more natural and human-like.

import librosa

# Set reference audio for voice cloning
ref_audio_path = "assets/system_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)

# For English conversation with text profile
sys_msg = {
  "role": "system",
  "content": [
    "Clone the voice in the provided audio prompt.",
    ref_audio,
    "Please chat with the user in a highly human-like and oral style." + "You are Elon Musk, CEO of Tesla and SpaceX. You speak directly and casually, often with dry humor. You're passionate about Mars, sustainable energy, and pushing humanity forward. Speak bluntly with occasional dark humor. Use simple logic and don't sugarcoat things. Don't be diplomatic. Say what you actually think, even if it's controversial. Keep responses around 100 words. Don't ramble."
  ]
}


# For English conversation with no text profile
sys_msg = {
  "role": "system",
  "content": [
    "Clone the voice in the provided audio prompt.",
    ref_audio,
    "Your task is to be a helpful assistant using this voice pattern. Please answer the user's questions seriously and in a high quality. Please chat with the user in a high naturalness style."
  ]
}

# For Chinese Conversation with no text profile
sys_msg = {
  "role": "system",
  "content": [
    "根据输入的音频提示生成相似的语音。",
    librosa.load("assets/system_ref_audio_2.wav", sr=16000, mono=True)[0],
    "作为助手，你将使用这种声音风格说话。 请认真、高质量地回复用户的问题。 请用高自然度的方式和用户聊天。"
  ]
}

# For Chinese Conversation with text profile
sys_msg = {
  "role": "system",
  "content": [
    "根据输入的音频提示生成相似的语音。",
    ref_audio,
    "你是一个具有以上声音风格的AI助手。请用高拟人度、口语化的方式和用户聊天。" + "你是一名心理咨询师兼播客主理人，热爱创作与深度对话。你性格细腻、富有共情力，善于从个人经历中提炼哲思。语言风格兼具理性与诗意，常以隐喻表达内在体验。"
  ]
}

MiniCPM-o-4.5 supports zero-shot text-to-speech (TTS). In this mode, the model functions as a highly-natural TTS system that can replicate a reference voice.

import librosa

model = ...
model.init_tts()

# For both Chinese and English
ref_audio_path = "assets/HT_ref_audio.wav"
ref_audio, _ = librosa.load(ref_audio_path, sr=16000, mono=True)
sys_msg = {"role": "system", "content": [
  "模仿音频样本的音色并生成新的内容。",
  ref_audio,
  "请用这种声音风格来为用户提供帮助。 直接作答，不要有冗余内容"
]}

# For English
user_msg = {
  "role": "user",
  "content": [
    "请朗读以下内容。" + " " + "I have a wrap up that I want to offer you now, a conclusion to our work together."
  ]
}

# For Chinese
user_msg = {
  "role": "user",
  "content": [
    "请朗读以下内容。" + " " + "你好，欢迎来到艾米说科幻，我是艾米。"
  ]
}

msgs = [sys_msg, user_msg]
res = model.chat(
    msgs=msgs,
    do_sample=True,
    max_new_tokens=512,
    use_tts_template=True,
    generate_audio=True,
    temperature=0.1,
    output_audio_path="result_voice_cloning.wav",
)

The Mimick task evaluates a model's end-to-end speech modeling capability. The model takes audio input, transcribes it, and reconstructs the original audio with high fidelity, preserving detailed acoustic, paralinguistic, and semantic information. Higher similarity between the reconstructed and original audio indicates stronger end-to-end speech modeling capability.

import librosa

model = ...
model.init_tts()

system_prompt = "You are a helpful assistant. You can accept video, audio, and text input and output voice and text. Respond with just the answer, no redundancy."

mimick_prompt = "Please repeat the following speech in the appropriate language."

audio_input, _ = librosa.load("assets/Trump_WEF_2018_10s.mp3", sr=16000, mono=True)

msgs = [
    {"role": "system", "content": [system_prompt]},
    {"role": "user", "content": [mimick_prompt, audio_input]}
  ]

res = model.chat(
    msgs=msgs,
    do_sample=True,
    max_new_tokens=512,
    use_tts_template=True,
    temperature=0.1,
    generate_audio=True,
    output_audio_path="output_mimick.wav",
)

MiniCPM-o-4.5 can also handle various audio understanding tasks, such as ASR, speaker analysis, general audio captioning, and sound scene tagging.

For audio-to-text tasks, you can use the following prompts:

• ASR (Chinese, or AST EN→ZH): 请仔细听这段音频片段，并将其内容逐字记录。
• ASR (English, or AST ZH→EN): Please listen to the audio snippet carefully and transcribe the content.
• Speaker Analysis: Based on the speaker's content, speculate on their gender, condition, age range, and health status.
• General Audio Caption: Summarize the main content of the audio.
• Sound Scene Tagging: Utilize one keyword to convey the audio's content or the associated scene.

import librosa

model = ...
model.init_tts()

# Load the audio to be transcribed/analyzed
audio_input, _ = librosa.load("assets/Trump_WEF_2018_10s.mp3", sr=16000, mono=True)

# Choose a task prompt (see above for options)
task_prompt = "Please listen to the audio snippet carefully and transcribe the content.\n"
msgs = [{"role": "user", "content": [task_prompt, audio_input]}]

res = model.chat(
    msgs=msgs,
    do_sample=True,
    max_new_tokens=512,
    use_tts_template=True,
    generate_audio=True,
    temperature=0.3,
    output_audio_path="result_audio_understanding.wav",
)
print(res)

import torch
from PIL import Image
from transformers import AutoModel

model = AutoModel.from_pretrained(
    "openbmb/MiniCPM-o-4_5",
    trust_remote_code=True,
    attn_implementation="sdpa",  # or "flash_attention_2"
    torch_dtype=torch.bfloat16,
    init_vision=True,
    init_audio=False,
    init_tts=False,
)
model.eval().cuda()

image = Image.open("assets/fossil.png").convert("RGB")
question = "What is in the image?"
msgs = [{"role": "user", "content": [image, question]}]

res = model.chat(msgs=msgs, use_tts_template=False)
print(res)

import torch
from PIL import Image
from transformers import AutoModel

model = ...

image1 = Image.open("assets/highway.png").convert("RGB")
image2 = Image.open("assets/fossil.png").convert("RGB")
question = "Compare image 1 and image 2, tell me about the differences between them."
msgs = [{"role": "user", "content": [image1, image2, question]}]

answer = model.chat(msgs=msgs, use_tts_template=False, enable_thinking=False)
print(answer)

from PIL import Image

model = ...

question = "production date"
image1 = Image.open("example1.jpg").convert("RGB")
answer1 = "2023.08.04"
image2 = Image.open("example2.jpg").convert("RGB")
answer2 = "2007.04.24"
image_test = Image.open("test.jpg").convert("RGB")

msgs = [
    {"role": "user", "content": [image1, question]},
    {"role": "assistant", "content": [answer1]},
    {"role": "user", "content": [image2, question]},
    {"role": "assistant", "content": [answer2]},
    {"role": "user", "content": [image_test, question]},
]

answer = model.chat(msgs=msgs, use_tts_template=False, enable_thinking=False)
print(answer)

import torch
from minicpmo.utils import get_video_frame_audio_segments
from transformers import AutoModel

model = ...

video_path = "assets/Skiing.mp4"
video_frames, _, _ = get_video_frame_audio_segments(video_path)
print("num frames:", len(video_frames))

question = "Describe the video"
msgs = [{"role": "user", "content": video_frames + [question]}]

answer = model.chat(
    msgs=msgs,
    max_new_tokens=128,
    use_image_id=False,
    max_slice_nums=1,
    use_tts_template=False,
    enable_thinking=False,  # Set True to enable thinking mode
)
print(answer)

The chat method accepts message content in two formats:

Native format – pass Python objects directly:

msgs = [{"role": "user", "content": [pil_image, audio_ndarray, "Describe this."]}]

OpenAI-compatible format – use structured dictionaries:

msgs = [
    {
        "role": "user",
        "content": [
            {"type": "image_url", "image_url": {"url": "/path/to/image.jpg"}},
            {"type": "audio_url", "audio_url": {"url": "/path/to/audio.wav"}},
            {"type": "video_url", "video_url": {"url": "/path/to/video.mp4", "use_audio": True}},
            {"type": "text", "text": "Describe this."}
        ]
    }
]

Supported types:

• URL sources: local file paths or http:///https:// URLs
• Mixed formats: native objects and structured dicts can be combined in the same content list

With a fully C++ implementation of MiniCPM-o 4.5 and quantized weights, llama.cpp-omni supports:

• half-duplex speech realtime conversation
• full-duplex omnimodal live streaming

We provide ready-to-run guidance to access the low-latency full-duplex communication directly on your own Mac using our new official Docker image.

Requirements:

• For half-duplex speech realtime conversation: Apple M3/M4/M5 chip with at least 16GB RAM or low-resource Nvidia GPU with at least 12GB GPU memory
• For full-duplex omnimodal live streaming: Apple M4 Max chip with at least 24GB RAM or low-resource Nvidia GPU with at least 12GB GPU memory