Convert a PDF to Markdown
Turn a document into reusable text with its footnotes.
Convert this PDF [public link] to Markdown, keeping its footnotes. When it is ready, summarize [question] from the document.
Leina connects to OOMOL Fusion API to help you convert PDFs and create images from a brief. Ask in your team chat. Leina does the work and brings back the result.
Connect OOMOL Fusion API, choose what to share, and hand off your first task.
You
Convert this PDF [public link] to Markdown with footnotes. Summarize its supplier onboarding steps.
Leina
The conversion is complete. I extracted the onboarding steps and retained the footnotes.
Fusion API · Markdown
Supplier guide
The guide’s onboarding checklist is ready to reuse.
A Fusion API AI agent can turn a PDF into readable text or create an image from your visual brief, retrieving completed work for you.
You specify the source and the destination. Leina uses the content available to your connection and returns the result for you to review.
OOMOL Fusion API brings document conversion and image, audio, and video tools into one service.
Visit Provider Website ↗Provide an accessible document link and your question.
Wait for conversion to finish and retrieve the text.
Review the requested sections alongside the converted document.
Copy a prompt, add your details, and send it to Leina in your connected team chat.
Turn a document into reusable text with its footnotes.
Convert this PDF [public link] to Markdown, keeping its footnotes. When it is ready, summarize [question] from the document.
Describe the subject, style, and composition for a finished image.
Create one image showing [scene] in [style], with [composition] at [size]. Give me the finished image.
Your next OOMOL Fusion API task can start with a message.
Tell Leina what you need in your team chat. Include the source, destination, and expected result.
Use an AI product configured for OOMOL Fusion API and authenticated with OOMOL access.
Share the source material, say where the result belongs, and describe what you need.
Review the result and any changes in the connected app.
Hand off these everyday tasks to your AI employee.
Recognize text from a single image.
Get doubao-stt task result
Get doubao-stt task state
Convert speech to text with Doubao
Generate, edit or decompose images with Seedream Pro or Flash
Get doubao-tts task result
Get doubao-tts task state
Convert text to speech with Doubao
Get fal-aura-sr task result
Get fal-aura-sr task state
Image super-resolution upscaling
Get fal-nano-banana-2 task result
Get fal-nano-banana-2 task state
Generate or edit images with Nano Banana 2
Get fal-nano-banana-pro task result
Get fal-nano-banana-pro task state
Edit images with Nano Banana Pro
Get fal-nano-banana task result
Get fal-nano-banana task state
Edit images with Nano Banana
Get the Qwen Image Layered task result
Get the Qwen Image Layered task state
Split an image into multiple layers with Qwen Image Layered
Image with background removed
Get fal-remove-background task state
Remove image backgrounds with the Fal.ai BRIA model
Abort multipart upload
Complete multipart upload
Initialize multipart upload
Generate a presigned URL for file upload
Generate a presigned URL for multipart upload parts
Read and extract URL content
Search web content
Get asynchronous OpenAI image generation result
Submit asynchronous OpenAI image generation requests, including gpt-image-2 and gpt-image-2.5 image creation.
Get asynchronous OpenAI image edit result
Submit asynchronous OpenAI image edit requests, including gpt-image-2 and gpt-image-2.5 image editing.
Get pdf-transform-epub task result
Get pdf-transform-epub task state
Convert a PDF to EPUB format
Get pdf-transform-markdown task result
Get pdf-transform-markdown task state
Convert a PDF to Markdown format
Get Qwen ASR file transcription task result
Get Qwen ASR file transcription task state
Submit a long-audio speech recognition task with Qwen ASR file transcription
Analyze documents with Tongyi Qianwen
Edit images with Tongyi Wanxiang
Generate images with Tongyi Qianwen
Get qwen-mt-image task result
Get qwen-mt-image task state
Image machine translation
Generate speech audio with CosyVoice TTS.
Generate speech audio
Create a Qwen voice design voice and return preview audio.
Generate speech audio using a Qwen voice design voice.
List cloned and designed custom voices.
Query custom voice details and deployment status.
Delete a custom voice.
Create a custom Qwen-Audio voice. Return its ID even if preview generation fails.
Query a Seedance video generation task result
Get a Seedance video generation task state
Generate videos with Doubao Seedance
Compress PNG images with the Tinify API
Query first-frame-to-video task result
Get wanx-i2v-video task state
Generate videos from the first frame with Tongyi Wanxiang
Get wanx-image task result
Get wanx-image task state
Generate and edit images with Tongyi Wanxiang AI
Get wanx-kf2v-video task result
Get wanx-kf2v-video task state
Generate videos from keyframes with Tongyi Wanxiang
Query reference-to-video task result
Get wanx-r2v-video task state
Generate videos from reference assets with Tongyi Wanxiang
Query text-to-video task result
Get wanx-t2v-video task state
Generate text-to-video videos with Tongyi Wanxiang
Get image text recognition and Chinese typo correction results
Recognize image text and suggest corrections for Chinese typos
Connect the Apps your work depends on, and give Leina the context to carry the task forward.
Hand off a task while your team is discussing it. Leina uses your connected tools and brings the result back to the conversation.
See How Leina Works in SlackThe conversion is complete. I extracted the onboarding steps and retained the footnotes.
Provide a publicly accessible PDF link so the conversion service can read it.
Some conversions and media jobs take time. The assistant retrieves the output after processing finishes.
Start with one task you already need to do. Tell Leina what a finished result should look like.
Connect OOMOL Fusion API, choose what to share, and hand off your first task.