Give an assistant a document, image, recording, or text and specify the information or output you need. Qwen models handle the corresponding extraction, translation, or media task.
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Read text from an image and organize the fields you specify into a structured result.
/oo Qwen: Use Qwen to read this image: [public image URL]. Extract [field names] into a structured table and flag text that is unclear.
Translate text for a specified audience using the terminology and context you provide.
/oo Qwen: Translate this text into [target language] with Qwen: [text]. Use these terminology pairs: [source and target terms]. Keep the meaning and match this context: [audience or domain].
Convert an accessible audio or video recording into text with sentence timings for review.
/oo Qwen: Transcribe this recording with Qwen: [public audio or video URL]. The likely language is [language]. Wait for completion and return the transcript with sentence timings.
Read a supplied document and organize the details you need to review.
/oo Qwen: Use Qwen to review this project document: [public document URL]. Extract the decisions, owners, and deadlines, marking anything not stated in the document.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →Connect a Beijing Model Studio API key, or use selected Qwen tasks through OOMOL Marketplace.
Connect Qwen →Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
This connection exposes task-specific Qwen models for OCR, document analysis, translation, image generation, speech synthesis, and transcription. It also supports custom voice management on your own connection.
Extract image text, analyze documents, and transcribe audio or video with timing information.
Translate text with terminology guidance or translate the text in an image and retrieve the resulting image.
Generate or edit images, synthesize speech, and create or list custom voices on your own connection.
Extract text and structured information from an image with Qwen3.5-OCR.
Leina 
Wanta 
qwen.extract_text Translate text with Qwen-MT and optional terminology, translation memory, and domain guidance.
qwen.translate_text Generate or edit images with the Qwen Image 3.0 family.
qwen.generate_image Generate speech with Qwen-Audio 3.0 TTS.
qwen.generate_speech Analyze documents or text with Qwen-Doc-Turbo.
qwen.analyze_document Create a Qwen-Audio custom voice from a public audio sample.
qwen.create_voice_clone Create a Qwen-Audio custom voice from a text description.
qwen.create_designed_voice List Qwen-Audio cloned and designed voices together.
qwen.list_custom_voices Get one Qwen-Audio cloned or designed voice.
qwen.get_custom_voice Delete one Qwen-Audio cloned or designed voice.
qwen.delete_custom_voice Submit a Qwen-Audio 3.0 asynchronous audio or video transcription task.
qwen.submit_speech_recognition Retrieve a Qwen-Audio 3.0 transcription task and its normalized result.
qwen.get_speech_recognition Submit an asynchronous Qwen image translation task.
qwen.submit_image_translation Retrieve a Qwen image translation task state and output.
qwen.get_image_translation No matching tools.
Tools are available through the OOMOL marketplace. Usage charges may apply.
Yes. Provide an accessible image URL and describe the fields or structured format you want. Review unclear or missing text against the source image before relying on the result.
Yes. Text translation accepts terminology pairs, translation memory, and domain guidance. Image translation also supports required terminology and text that should stay unchanged.
The result includes recognized text by audio channel and sentence timings. Speaker labels can be requested when diarization is enabled; recognition quality depends on the recording.
Custom voice creation and management require your own Qwen connection. Marketplace covers speech generation and the other extraction, translation, image, document, and transcription tasks.
Manage which optional storage OOMOL can use. You can change these choices from the footer at any time.