What problem does it solve? Integrating Alibaba Cloud DashScope (Bailian) media models is error-prone because image generation, TTS, and ASR use DashScope-native endpoints rather than the OpenAI-compatible path, each with different request bodies, size formats, and async polling patterns. This Skill documents the exact endpoints, parameters, and pitfalls so you can call Qwen-Image, Qwen-TTS, and Qwen-ASR correctly on the first attempt. ## Core Features & Use Cases - Image Generation: Call qwen-image-2.0-pro and related models with correct size formatting ("1024*1024"), prompt extension, negative prompts, and seed control. - Text-to-Speech: Synthesize narration with qwen3-tts-flash using selectable voices and language types, returning a downloadable WAV URL. - ASR with Word Timestamps: Transcribe publicly hosted audio via the async qwen3-asr-flash-filetrans model, polling the task endpoint and normalizing millisecond timestamps to seconds for subtitle generation. - Use Case: Build a video pipeline where you generate cover images, narrate a script with TTS, then transcribe the narration to produce word-timed subtitles. ## Quick Start Set DASHSCOPE_API_KEY in your .env file, then ask the agent to generate an image with the dashscope provider, synthesize narration with a chosen voice, or transcribe a public audio URL with word-level timestamps.
