Supply a document URL or visual brief to extract text or generate media through the operations available in your product.
Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.
Submit a public PDF and retrieve the completed text conversion.
/oo OOMOL Fusion API: Convert [public PDF URL] to Markdown through Fusion API, including footnotes. Check the task state until completed, retrieve the result, and summarize [question] using that content.
Create an image using Seedream through the Fusion API operation.
/oo OOMOL Fusion API: Use Fusion API Seedream to generate an image of [scene, composition, and style] at [size]. Request one image and provide the generated result.
Set up oo CLI and the oo Skill in your agent.
Install OOMOL →Use an AI product configured for OOMOL Fusion API and authenticated with OOMOL access.
Connect OOMOL Fusion API →Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →Choose Your Agent
The connection routes document, image, audio, and video operations through OOMOL Fusion API. Some operations respond directly; background jobs require a session ID to query state and results.
Recognize text from an image or convert a PDF through a background job.
Generate Seedream images or submit and retrieve Seedance video tasks.
Get cphone-nano-banana task result
Leina 
Wanta 
fusion-api.cphone_nano_banana_result Get cphone-nano-banana task state
fusion-api.cphone_nano_banana_state Edit images with Nano Banana
fusion-api.cphone_nano_banana_submit Recognize text from a single image.
fusion-api.deepseek_ocr_recognize Get doubao-stt task result
fusion-api.doubao_stt_result Get doubao-stt task state
fusion-api.doubao_stt_state Convert speech to text with Doubao
fusion-api.doubao_stt_submit Generate images from text with Doubao Seedream
fusion-api.doubao_text_to_image_seedream_generate Get doubao-tts task result
fusion-api.doubao_tts_result Get doubao-tts task state
fusion-api.doubao_tts_state Convert text to speech with Doubao
fusion-api.doubao_tts_submit Get fal-aura-sr task result
fusion-api.fal_aura_sr_result Get fal-aura-sr task state
fusion-api.fal_aura_sr_state Image super-resolution upscaling
fusion-api.fal_aura_sr_submit Get fal-nano-banana-2 task result
fusion-api.fal_nano_banana_2_result Get fal-nano-banana-2 task state
fusion-api.fal_nano_banana_2_state Generate or edit images with Nano Banana 2
fusion-api.fal_nano_banana_2_submit Get fal-nano-banana-pro task result
fusion-api.fal_nano_banana_pro_result Get fal-nano-banana-pro task state
fusion-api.fal_nano_banana_pro_state Edit images with Nano Banana Pro
fusion-api.fal_nano_banana_pro_submit Get fal-nano-banana task result
fusion-api.fal_nano_banana_result Get fal-nano-banana task state
fusion-api.fal_nano_banana_state Edit images with Nano Banana
fusion-api.fal_nano_banana_submit Get the Qwen Image Layered task result
fusion-api.fal_qwen_image_layered_result Get the Qwen Image Layered task state
fusion-api.fal_qwen_image_layered_state Split an image into multiple layers with Qwen Image Layered
fusion-api.fal_qwen_image_layered_submit Image with background removed
fusion-api.fal_remove_background_result Get fal-remove-background task state
fusion-api.fal_remove_background_state Remove image backgrounds with the Fal.ai BRIA model
fusion-api.fal_remove_background_submit Abort multipart upload
fusion-api.file_upload_abort_multipart_upload Complete multipart upload
fusion-api.file_upload_complete_multipart_upload Initialize multipart upload
fusion-api.file_upload_create_multipart_upload Generate a presigned URL for file upload
fusion-api.file_upload_generate_presigned_url Generate a presigned URL for multipart upload parts
fusion-api.file_upload_generate_presigned_urls Read and extract URL content
fusion-api.jina_reader_read Search web content
fusion-api.jina_reader_search Get asynchronous OpenAI image generation result
fusion-api.openai_image_async_result Submit asynchronous OpenAI image generation requests, including gpt-image-2 and gpt-image-2.5 image creation.
fusion-api.openai_image_async_submit Get asynchronous OpenAI image edit result
fusion-api.openai_image_edit_async_result Submit asynchronous OpenAI image edit requests, including gpt-image-2 and gpt-image-2.5 image editing.
fusion-api.openai_image_edit_async_submit Get pdf-transform-epub task result
fusion-api.pdf_transform_epub_result Get pdf-transform-epub task state
fusion-api.pdf_transform_epub_state Convert a PDF to EPUB format
fusion-api.pdf_transform_epub_submit Get pdf-transform-markdown task result
fusion-api.pdf_transform_markdown_result Get pdf-transform-markdown task state
fusion-api.pdf_transform_markdown_state Convert a PDF to Markdown format
fusion-api.pdf_transform_markdown_submit Get Qwen ASR file transcription task result
fusion-api.qwen_asr_filetrans_result Get Qwen ASR file transcription task state
fusion-api.qwen_asr_filetrans_state Submit a long-audio speech recognition task with Qwen ASR file transcription
fusion-api.qwen_asr_filetrans_submit Analyze documents with Tongyi Qianwen
fusion-api.qwen_doc_turbo_analyze Edit images with Tongyi Wanxiang
fusion-api.qwen_image_edit_plus_edit Generate images with Tongyi Qianwen
fusion-api.qwen_image_generate Get qwen-mt-image task result
fusion-api.qwen_mt_image_result Get qwen-mt-image task state
fusion-api.qwen_mt_image_state Image machine translation
fusion-api.qwen_mt_image_submit Generate speech audio with CosyVoice TTS.
fusion-api.cosyvoice_tts_generate Generate speech audio
fusion-api.qwen_tts_generate Create a Qwen voice design voice and return preview audio.
fusion-api.qwen_voice_design_create Generate speech audio using a Qwen voice design voice.
fusion-api.qwen_voice_design_generate List Qwen voice design voices.
fusion-api.qwen_voice_design_list Get details for a Qwen voice design voice.
fusion-api.qwen_voice_design_query Delete a Qwen voice design voice.
fusion-api.qwen_voice_design_delete Create a Qwen voice cloning voice and return a preview audio URL.
fusion-api.qwen_voice_cloning_create Query a Seedance video generation task result
fusion-api.seedance_video_result Get a Seedance video generation task state
fusion-api.seedance_video_state Generate videos with Doubao Seedance
fusion-api.seedance_video_submit Compress PNG images with the Tinify API
fusion-api.tinify_png_shrink_compress Query first-frame-to-video task result
fusion-api.wanx_i2v_video_result Get wanx-i2v-video task state
fusion-api.wanx_i2v_video_state Generate videos from the first frame with Tongyi Wanxiang
fusion-api.wanx_i2v_video_submit Get wanx-image task result
fusion-api.wanx_image_result Get wanx-image task state
fusion-api.wanx_image_state Generate and edit images with Tongyi Wanxiang AI
fusion-api.wanx_image_submit Get wanx-kf2v-video task result
fusion-api.wanx_kf2v_video_result Get wanx-kf2v-video task state
fusion-api.wanx_kf2v_video_state Generate videos from keyframes with Tongyi Wanxiang
fusion-api.wanx_kf2v_video_submit Query reference-to-video task result
fusion-api.wanx_r2v_video_result Get wanx-r2v-video task state
fusion-api.wanx_r2v_video_state Generate videos from reference assets with Tongyi Wanxiang
fusion-api.wanx_r2v_video_submit Query text-to-video task result
fusion-api.wanx_t2v_video_result Get wanx-t2v-video task state
fusion-api.wanx_t2v_video_state Generate text-to-video videos with Tongyi Wanxiang
fusion-api.wanx_t2v_video_submit No matching tools.
This connection uses OOMOL access supplied by your product rather than a separate provider key. The product must be configured for Fusion API.
Keep the session ID from submission, check state, and retrieve the result after completion.
Supply a publicly accessible PDF URL so the conversion service can retrieve the document.
Manage which optional storage OOMOL can use. You can change these choices from the footer at any time.