Dashscope
Connect Dashscope to harness Alibaba Cloud's Qwen models for multimodal content creation. Generate images via qwen-image-2.0-pro, synthesize speech with qwen3-tts-flash, or transcribe audio with word-level timing via qwen3-asr-flash-filetrans—all through native DashScope endpoints.
Dashscope integrates Alibaba Cloud's Qwen models for image generation, text-to-speech, and speech-to-text with word-level timestamps.
AI-generated summary based on this skill's SKILL.md
Install
calesthio/OpenMontage/dashscope · repository language: Python
git clone https://github.com/calesthio/OpenMontage
cp -r OpenMontage ~/.claude/skills/dashscopegenerated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub
npx skillfed install calesthio/OpenMontage/dashscopeFrequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is Dashscope and what can it do?
Dashscope connects you to Alibaba Cloud's Qwen models for multimodal content creation. It enables image generation via qwen-image-2.0-pro, speech synthesis with qwen3-tts-flash, and audio transcription with word-level timing via qwen3-asr-flash-filetrans through native DashScope endpoints.
How do I integrate Dashscope with my agent or workflow?
Dashscope integrates as a connector into your agent or workflow, allowing you to call Alibaba Cloud's Qwen models directly. Configure it with your DashScope API credentials, then invoke image generation, text-to-speech, or speech-to-text capabilities as steps in your automation pipeline.
How to use Dashscope for image generation and audio tasks?
Dashscope provides three primary functions: generate images using qwen-image-2.0-pro, synthesize speech with qwen3-tts-flash, and transcribe audio with word-level timing via qwen3-asr-flash-filetrans. Each integrates into your workflow as a discrete tool you can chain with other steps.
What is the dashscope configuration process?
Configure Dashscope by providing your DashScope API credentials and selecting which Qwen model endpoint you need—qwen-image-2.0-pro for images, qwen3-tts-flash for speech synthesis, or qwen3-asr-flash-filetrans for audio transcription. Once set up, the skill is ready to use in your agent.
Is Dashscope open source and what license does it use?
Dashscope is released under the AGPL-3.0 license, making it open source. This means you can use, modify, and distribute it freely under the terms of the AGPL-3.0 agreement.
Can Dashscope handle multimodal content creation?
Yes, Dashscope is built for multimodal content creation. It supports image generation, text-to-speech synthesis, and speech-to-text transcription all within a single skill, letting you combine these capabilities in complex workflows.