Alicloud Ai Multimodal Qwen Omni

Name: Alicloud Ai Multimodal Qwen Omni
Author: cinience

cinience/alicloud-skills

93 installs
396 repo stars
Updated July 18, 2026
cinience/alicloud-skills

Prepares all-in-one multimodal requests for Alibaba Cloud Model Studio Qwen Omni models for image-plus-audio interaction and realtime multimodal agents.

About

Builds multimodal understanding and generation requests against Alibaba Cloud Model Studio Qwen Omni models. A developer uses it for image-plus-audio interaction, voice assistants, and realtime multimodal agents.

Targets Qwen Omni all-in-one multimodal models
Includes py_compile validation and evidence output

Alicloud Ai Multimodal Qwen Omni by the numbers

93 all-time installs (skills.sh)
Ranked #4,673 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
Data as of Aug 5, 2026 (Skillselion catalog sync)

npx skills add https://github.com/cinience/alicloud-skills --skill alicloud-ai-multimodal-qwen-omni

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

[![Listed on Skillselion](https://skillselion.com/badge/skills/cinience/alicloud-skills/alicloud-ai-multimodal-qwen-omni.svg)](https://skillselion.com/skills/cinience/alicloud-skills/alicloud-ai-multimodal-qwen-omni)

Installs	93
repo stars	★ 396
Last updated	July 18, 2026
Repository	cinience/alicloud-skills ↗

What it does

Prepares all-in-one multimodal requests for Alibaba Cloud Model Studio Qwen Omni models for image-plus-audio interaction and realtime multimodal agents.

Files

SKILL.mdMarkdownGitHub ↗

Category: provider

Model Studio Qwen Omni

Validation

mkdir -p output/alicloud-ai-multimodal-qwen-omni
python -m py_compile skills/ai/multimodal/alicloud-ai-multimodal-qwen-omni/scripts/prepare_omni_request.py && echo "py_compile_ok" > output/alicloud-ai-multimodal-qwen-omni/validate.txt

Pass criteria: command exits 0 and output/alicloud-ai-multimodal-qwen-omni/validate.txt is generated.

Critical model names

Use one of these exact model strings:

qwen3-omni-flash
qwen3-omni-flash-realtime
qwen-omni-turbo
qwen-omni-turbo-realtime

Typical use

Image + audio + text assistant
Realtime multimodal agents
Spoken responses grounded in visual input

Normalized interface (omni.chat)

Request

model (string, optional): default qwen3-omni-flash
text (string, optional)
image (string, optional)
audio (string, optional)
response_modalities (array<string>, optional): e.g. ["text"], ["text","audio"]

Response

text (string, optional)
audio_url or audio_chunk (optional)
usage (object, optional)

Quick start

python skills/ai/multimodal/alicloud-ai-multimodal-qwen-omni/scripts/prepare_omni_request.py \
  --output output/alicloud-ai-multimodal-qwen-omni/request.json

References

references/sources.md

interface:
  display_name: "Alibaba Cloud AI Multimodal Qwen Omni"
  short_description: "All-in-one multimodal interaction with Qwen Omni"
  default_prompt: "Use $alicloud-ai-multimodal-qwen-omni to complete this ai/multimodal omni task on Alibaba Cloud."

#!/usr/bin/env python3
"""Prepare a minimal request payload for Qwen Omni."""

from __future__ import annotations

import argparse
import json
from pathlib import Path

DEFAULT_PAYLOAD = {
    "model": "qwen3-omni-flash",
    "text": "Describe the input briefly and answer in Chinese.",
    "image": "https://example.com/demo.jpg",
    "response_modalities": ["text"],
}


def main() -> None:
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--output",
        default="output/alicloud-ai-multimodal-qwen-omni/request.json",
    )
    args = parser.parse_args()

    output = Path(args.output)
    output.parent.mkdir(parents=True, exist_ok=True)
    output.write_text(json.dumps(DEFAULT_PAYLOAD, ensure_ascii=False, indent=2), encoding="utf-8")
    print(output)


if __name__ == "__main__":
    main()