Aliyun Qwen Livetranslate

Use when live speech translation is needed with Alibaba Cloud Model Studio Qwen LiveTranslate models, including bilingual meetings, realtime interpretation,...

Security Scan

The skill is internally coherent: it only prepares a Qwen LiveTranslate request payload and contains no unrelated credential requests, network calls, or install steps.

Purpose & Capability

Name/description (Alibaba Qwen LiveTranslate) match the included files: a small helper script and SKILL.md that prepare request payloads for the stated models. The skill does not claim to perform actual network calls, and nothing bundled would require unrelated capabilities.

Instruction Scope

Runtime instructions only validate and compile the included Python script and save request/response artifacts under output/aliyun-qwen-livetranslate/. The instructions do not read unrelated files, access extra environment variables, or send data to external endpoints.

Install Mechanism

No install spec or external downloads; the only code is a small local Python script (1 KB) that writes a JSON payload. Low installation risk.

Credentials

The skill requests no environment variables or credentials. Note: to actually call Alibaba Cloud Model Studio APIs in a real integration you would need to provide appropriate Alibaba credentials elsewhere; the absence of credential requests here is consistent with this skill being a local payload preparer but means the skill alone won't perform live networked translation.

Persistence & Privilege

always is false and the skill does not request persistent or elevated privileges, nor does it modify other skills or system-wide settings.

Assessment

This skill is low-risk and does only one thing: create a minimal JSON request for Qwen LiveTranslate models. It does not perform network calls or ask for credentials — you will need to supply Alibaba Cloud credentials (in a separate, appropriate integration) if you want actual translation requests to be sent. Before installing, confirm you trust the source of the skill (source is unknown) and that any later integration that performs network calls will handle credentials securely. If you expect the skill to perform live streaming or API calls, verify where those calls will run and what credentials they require.

Category: provider

Model Studio Qwen LiveTranslate

Validation

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

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

Output And Evidence

• Save translation session payloads and response summaries under output/aliyun-qwen-livetranslate/.

Critical model names

Use one of these exact model strings:

• qwen3-livetranslate-flash
• qwen3-livetranslate-flash-realtime

Typical use

• Chinese/English meeting interpretation
• Live subtitles in another language
• Call-center agent assist with translated captions

Normalized interface (audio.livetranslate)

Request

• model (string, optional): default qwen3-livetranslate-flash
• source_language (string, required)
• target_language (string, required)
• audio_format (string, optional): e.g. pcm
• sample_rate (int, optional): e.g. 16000

Response

• translated_text (string)
• source_text (string, optional)
• audio_url or audio_chunk (optional, model dependent)

Quick start

python skills/ai/audio/aliyun-qwen-livetranslate/scripts/prepare_livetranslate_request.py \
  --source-language zh \
  --target-language en \
  --output output/aliyun-qwen-livetranslate/request.json

Notes

• Prefer the realtime model for continuous streaming sessions.
• Prefer the non-realtime flash model for simpler integration and lower client complexity.

References

• references/sources.md