Aliyun Qwen Asr Realtime

Name: Aliyun Qwen Asr Realtime
Author: cinience

cinience/alicloud-skills

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

Run low-latency realtime speech recognition with Alibaba Cloud Model Studio Qwen ASR Realtime models for streaming input, live captions, and voice agents.

About

Uses Model Studio Qwen ASR Realtime models for streaming, low-latency speech-to-text over microphone or duplex voice input. A developer uses it for live captions and voice-agent input.

qwen3-asr-flash-realtime model strings
Targets realtime subtitles, captions, and duplex voice agents

Aliyun Qwen Asr Realtime by the numbers

53 all-time installs (skills.sh)
Ranked #6,979 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 aliyun-qwen-asr-realtime

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/aliyun-qwen-asr-realtime.svg)](https://skillselion.com/skills/cinience/alicloud-skills/aliyun-qwen-asr-realtime)

Installs	53
repo stars	★ 396
Last updated	July 18, 2026
Repository	cinience/alicloud-skills ↗

What it does

Run low-latency realtime speech recognition with Alibaba Cloud Model Studio Qwen ASR Realtime models for streaming input, live captions, and voice agents.

Files

SKILL.mdMarkdownGitHub ↗

Category: provider

Model Studio Qwen ASR Realtime

Validation

mkdir -p output/aliyun-qwen-asr-realtime
python -m py_compile skills/ai/audio/aliyun-qwen-asr-realtime/scripts/prepare_realtime_asr_request.py && echo "py_compile_ok" > output/aliyun-qwen-asr-realtime/validate.txt

Pass criteria: command exits 0 and output/aliyun-qwen-asr-realtime/validate.txt is generated.

Output And Evidence

Save session payloads and response samples under output/aliyun-qwen-asr-realtime/.

Critical model names

Use one of these exact model strings:

qwen3-asr-flash-realtime
qwen3-asr-flash-realtime-2026-02-10

Use cases

Realtime subtitles and captions
Voice-agent duplex input
Streaming speech-to-text in browser or terminal clients

Prerequisites

Set DASHSCOPE_API_KEY in your environment, or add dashscope_api_key to ~/.alibabacloud/credentials.
Realtime sessions generally require WebSocket or streaming session handling in the client.

Normalized interface (asr.realtime)

Request

model (string, optional): default qwen3-asr-flash-realtime
language_hints (array<string>, optional)
format (string, optional): e.g. pcm, wav
sample_rate (int, optional): e.g. 16000
chunk_ms (int, optional): frame size in milliseconds

Response

text (string): recognized transcript fragment
is_final (bool): finalization marker
usage (object, optional)

Quick start

Generate a request template:

python skills/ai/audio/aliyun-qwen-asr-realtime/scripts/prepare_realtime_asr_request.py \
  --output output/aliyun-qwen-asr-realtime/request.json

Operational guidance

Prefer 16kHz mono PCM unless your client stack requires another format.
Keep chunks small enough for responsive partial results.
If you only have recorded files, use skills/ai/audio/aliyun-qwen-asr/ instead.

References

references/sources.md

interface:
  display_name: "Alibaba Cloud AI Audio ASR Realtime"
  short_description: "Realtime speech recognition with Qwen ASR Realtime"
  default_prompt: "Use $aliyun-qwen-asr-realtime to complete this ai/audio realtime ASR task on Alibaba Cloud."

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

from __future__ import annotations

import argparse
import json
from pathlib import Path

DEFAULT_PAYLOAD = {
    "model": "qwen3-asr-flash-realtime",
    "input_audio": {
        "format": "pcm",
        "sample_rate": 16000,
        "channels": 1,
    },
    "language_hints": ["zh", "en"],
    "chunk_ms": 100,
}


def main() -> None:
    parser = argparse.ArgumentParser()
    parser.add_argument(
        "--output",
        default="output/aliyun-qwen-asr-realtime/request.json",
        help="Path to write the sample request payload.",
    )
    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()