$npx -y skills add cinience/alicloud-skills --skill aliyun-qwen-livetranslateUse when live speech translation is needed with Alibaba Cloud Model Studio Qwen LiveTranslate models, including bilingual meetings, realtime interpretation, and speech-to-speech or speech-to-text translation flows.
| 1 | Category: provider |
| 2 | |
| 3 | # Model Studio Qwen LiveTranslate |
| 4 | |
| 5 | ## Validation |
| 6 | |
| 7 | ```bash |
| 8 | mkdir -p output/aliyun-qwen-livetranslate |
| 9 | 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 |
| 10 | ``` |
| 11 | |
| 12 | Pass criteria: command exits 0 and `output/aliyun-qwen-livetranslate/validate.txt` is generated. |
| 13 | |
| 14 | ## Output And Evidence |
| 15 | |
| 16 | - Save translation session payloads and response summaries under `output/aliyun-qwen-livetranslate/`. |
| 17 | |
| 18 | ## Critical model names |
| 19 | |
| 20 | Use one of these exact model strings: |
| 21 | - `qwen3-livetranslate-flash` |
| 22 | - `qwen3-livetranslate-flash-realtime` |
| 23 | |
| 24 | ## Typical use |
| 25 | |
| 26 | - Chinese/English meeting interpretation |
| 27 | - Live subtitles in another language |
| 28 | - Call-center agent assist with translated captions |
| 29 | |
| 30 | ## Normalized interface (audio.livetranslate) |
| 31 | |
| 32 | ### Request |
| 33 | - `model` (string, optional): default `qwen3-livetranslate-flash` |
| 34 | - `source_language` (string, required) |
| 35 | - `target_language` (string, required) |
| 36 | - `audio_format` (string, optional): e.g. `pcm` |
| 37 | - `sample_rate` (int, optional): e.g. `16000` |
| 38 | |
| 39 | ### Response |
| 40 | - `translated_text` (string) |
| 41 | - `source_text` (string, optional) |
| 42 | - `audio_url` or `audio_chunk` (optional, model dependent) |
| 43 | |
| 44 | ## Quick start |
| 45 | |
| 46 | ```bash |
| 47 | python skills/ai/audio/aliyun-qwen-livetranslate/scripts/prepare_livetranslate_request.py \ |
| 48 | --source-language zh \ |
| 49 | --target-language en \ |
| 50 | --output output/aliyun-qwen-livetranslate/request.json |
| 51 | ``` |
| 52 | |
| 53 | ## Notes |
| 54 | |
| 55 | - Prefer the realtime model for continuous streaming sessions. |
| 56 | - Prefer the non-realtime flash model for simpler integration and lower client complexity. |
| 57 | |
| 58 | ## References |
| 59 | |
| 60 | - `references/sources.md` |