Alicloud Ai Audio 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 a small, coherent helper that only builds a JSON request payload for Alibaba Cloud Qwen LiveTranslate and does not request credentials, install software, or perform network operations.

Purpose & Capability

The name/description (live speech translation with Alibaba Cloud Qwen LiveTranslate) matches the code and instructions: the script simply prepares a request payload containing model name, source/target languages, and audio parameters.

Instruction Scope

SKILL.md instructs generating and saving payloads under output/alicloud-ai-audio-livetranslate/ and validating Python compilation; it does not read unrelated files, access environment variables, or send data to external endpoints.

Install Mechanism

No install spec is present (instruction-only plus a small local script). Nothing is downloaded or written beyond the payload output directory created by the script.

Credentials

The skill requests no environment variables, no credentials, and no config paths. This is proportional to a helper that only creates local JSON payloads.

Persistence & Privilege

always is false and the skill does not modify other skills or global agent settings; it only writes its own output files under the declared output path.

Assessment

This skill is just a small helper that creates a JSON request for Alibaba Cloud Qwen LiveTranslate; it does not call Alibaba Cloud or store credentials. Before using it in production, note: (1) you'll need separate client code and Alibaba Cloud credentials to actually send audio and receive translations, (2) any real audio or sensitive text you process should be handled carefully because the skill writes files to output/alicloud-ai-audio-livetranslate/, and (3) if future versions add network calls or request environment variables (API keys), reassess those additions. If you expect the skill to perform streaming or authenticate automatically, understand it does not — it only prepares payloads.

Category: provider

Model Studio Qwen LiveTranslate

Validation

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

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

Output And Evidence

• Save translation session payloads and response summaries under output/alicloud-ai-audio-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/alicloud-ai-audio-livetranslate/scripts/prepare_livetranslate_request.py \
  --source-language zh \
  --target-language en \
  --output output/alicloud-ai-audio-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