Pemo guide

Capability map

Explore Pemo by feature: library, PDF translation, document-context Q&A, notes, media processing, batch tasks, local-first services, and enhanced retrieval.

Open a feature page

Library and workspaces

Start in the default workspace, then split materials by project, course, client, or sensitivity when needed.

  • Import PDFs, Word files, web pages, images, audio, and video
  • Open View All for table browsing
  • Filter by folder, tag, file type, and recent reading time

PDF translation and bilingual reading

Translate and read foreign PDFs, papers, textbooks, cases, and reports with terminology and page-range control.

  • Choose translation service, source language, and target language
  • Support terminology and page-range selection
  • Keep source PDF, translation, annotations, and notes in one reading flow

AI summaries and document-context Q&A

Pemo Q&A is not detached chat; it happens beside the current document, subtitles, notes, and library context.

  • Ask questions over the current PDF, subtitle, or file context
  • Generate summaries, structured notes, and mind maps
  • Manually review important answers against source content

Notes and knowledge organization

Turn reading, translation, and Q&A output into reusable notes with task-specific note styles.

  • Key points, study notes, action items, and researcher memos
  • Quoted note passages can locate the original PDF text
  • Useful for paper cards, meeting minutes, class review, and contract risk lists

Media transcription, subtitles, and voiceover

Turn meetings, class videos, podcasts, interviews, and tutorials into subtitles, then translate, edit, generate notes, and create voiceover.

  • Batch transcribe media files
  • Translate, edit, and style subtitles
  • Generate voiceover from source text or translation

Batch processing

Process paper collections, report packs, scanned files, and course materials with PDF batch translation, PDF batch conversion to Markdown, and media batch transcription.

  • Select multiple files and folders
  • Set task type, language, and page range
  • Check task progress in Task Management

Service configuration and local-first

Configure model, translation, transcription, TTS, and local services; choose local-first workflows for sensitive materials.

  • Configure OpenAI, DeepSeek, SiliconFlow, Qwen, Ollama, and other services
  • Combine local model Q&A, local transcription, and local voiceover when needed
  • Confirm data flow separately for cloud services, sync, and plugins

Enhanced retrieval

For long-document Q&A, configure Embedding retrieval and Rerank to find more relevant document chunks first.

  • Useful for long PDFs, internal reports, and meeting records
  • Retrieval finds material; the model answers based on material
  • Answers still require manual review against source content
Capability map | Guide