← 返回 Skills 市场

Alicloud Ai Audio Asr Realtime

Name: Alicloud Ai Audio Asr Realtime
Author: cinience

作者 cinience · GitHub ↗ · v1.0.0 · MIT-0

cross-platform ⚠ suspicious

321

总下载

当前安装

版本数

在 OpenClaw 中安装

/install alicloud-ai-audio-asr-realtime

功能描述

Use when low-latency realtime speech recognition is needed with Alibaba Cloud Model Studio Qwen ASR Realtime models, including streaming microphone input, li...

使用说明 (SKILL.md)

Category: provider

Model Studio Qwen ASR Realtime

Validation

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

Pass criteria: command exits 0 and output/alicloud-ai-audio-asr-realtime/validate.txt is generated.

Output And Evidence

Save session payloads and response samples under output/alicloud-ai-audio-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\x3Cstring>, 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/alicloud-ai-audio-asr-realtime/scripts/prepare_realtime_asr_request.py \
  --output output/alicloud-ai-audio-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/alicloud-ai-audio-asr/ instead.

References

references/sources.md

安全使用建议

This skill appears to implement what it claims (a tiny helper for Alibaba Cloud realtime ASR), but there are two practical issues to check before installing: (1) SKILL.md requires a DASHSCOPE_API_KEY or credentials file, yet the package metadata doesn't list any required env vars—confirm which credential(s) the skill actually needs and scope them minimally. (2) The validation command references a file path that doesn't match the included file layout, so the provided validation step may fail; verify the correct paths. Also be aware the skill instructs saving session payloads to output/, so decide whether storing transcripts/audio locally is acceptable and where those files will reside. If you need more assurance, ask the publisher to fix the metadata (declare DASHSCOPE_API_KEY) and correct the validation path.

功能分析

Type: OpenClaw Skill Name: alicloud-ai-audio-asr-realtime Version: 1.0.0 The skill bundle is a legitimate utility for interacting with Alibaba Cloud's Qwen ASR Realtime service. The included Python script (prepare_realtime_asr_request.py) simply generates a static JSON request template, and the SKILL.md instructions focus on standard operational procedures without any signs of prompt injection, data exfiltration, or unauthorized execution.

能力评估

ℹ Purpose & Capability

The name/description and included helper script align with realtime ASR on Alibaba Cloud Model Studio Qwen ASR. Asking for an API key or ~/.alibabacloud/credentials in the SKILL.md is appropriate for an Alibaba Cloud integration. However, the registry metadata claims no required environment variables or primary credential, which contradicts the SKILL.md.

⚠ Instruction Scope

SKILL.md is otherwise narrowly scoped (prepare a request JSON, guidance for streaming use). But two concerns: (1) the validation command references a path 'skills/ai/audio/alicloud-ai-audio-asr-realtime/scripts/prepare_realtime_asr_request.py' that does not match the bundled file location ('scripts/prepare_realtime_asr_request.py'), so the provided validation step may fail or mislead. (2) SKILL.md instructs the agent to 'Save session payloads and response samples under output/...', which is reasonable for debugging but means the skill will persist transcripts and possibly audio locally — users should be aware of that storage and retention.

✓ Install Mechanism

No install spec; the skill is instruction-only with a small helper script. This minimizes installer-related risk.

⚠ Credentials

The SKILL.md requires DASHSCOPE_API_KEY or ~/.alibabacloud/credentials, but the skill metadata declares no required env vars or primary credential. That mismatch is a red flag: either the metadata is incomplete (expected) or the SKILL.md is asking for credentials the registry doesn't advertise. Any API key should be scoped to the minimum required permissions and stored securely.

✓ Persistence & Privilege

always is false and the skill does not request system-wide changes or persistent/autonomous privileges. It writes output into an output/ subdirectory (as documented), which is normal for a helper tool.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install alicloud-ai-audio-asr-realtime
安装完成后，直接呼叫该 Skill 的名称或使用 /alicloud-ai-audio-asr-realtime 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

batch publish from alicloud-skills on 2026-03-11

元数据

Slug alicloud-ai-audio-asr-realtime

版本 1.0.0

许可证 MIT-0

累计安装 0

当前安装数 0

历史版本数 1

常见问题