Audeus vs PDF-ChatGPT
Audeus
audeus.comPDF-ChatGPT
github.comSide by side
| Figure | Audeus | PDF-ChatGPT |
|---|---|---|
| Price from | $9.92/mo | — |
| Free plan | Yes | — |
| Free trial | Yes | — |
| Open source | — | — |
| Web | Yes | Yes |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | — | Yes |
| iOS | Yes | — |
| Android | Yes | — |
| API | — | Yes |
| Self-hosted | — | Yes |
| Plans published | 4 | 0 |
| Spec score · AI PDF Assistants | 9.3 (#2) | 7.4 (#22) |
| Integrations | The pricing page lists Canva integration, while the Chrome extension page says it works with Google Docs and Gmail. | Out of the box, the project uses OpenAI embeddings and the OpenAI Responses API; the maker says adapting it to another LLM provider would require code changes. |
Plans
In their own words
Audeus
Audeus converts PDFs, documents, scans, screenshots, and other text into speech using AI voices. It supports PDF, Word (DOCX), and non-DRM EPUB files, and advertises more than 50 languages. As audio plays, spoken text is highlighted; playback speed can be adjusted, with Pro listing speeds up to 3.5x. Users can highlight documents, add notes and comments, and mark images or graphs with shape highlights. The app can scan printed material, including multiple pages in a batch. Listed platforms are Android, iOS, web, and an extension; the Chrome extension page says it works with Google Docs and Gmail, while Canva integration appears on the pricing page. Free includes standard voices, limited access to Pro voices, and limited document uploads. Pro is listed at $119.04 per year, billed annually ($9.92/month), and includes a three-day trial. The selected plan begins automatically after the trial unless canceled. The company offers volume-based pricing for teams and institutions.
PDF-ChatGPT
PDF-ChatGPT is a free, open-source, self-hosted application for asking natural-language questions about PDF files and receiving answers with document and page citations. It can index multiple PDFs and show document status, page counts, and chunk counts. Semantic search uses a persistent FAISS index, with a relevance threshold and optional per-document scoping. Answers come from OpenAI’s Responses API and can stream token by token; SQLite keeps conversation history for follow-up questions. The browser interface renders Markdown, offers dark and light themes, and adapts to mobile and tablet layouts. Uploaded PDFs, the index, and conversation history are stored locally, but text is sent to OpenAI for embeddings and chat generation. An OpenAI API key with billing enabled is required, and token use is metered. Uploads must be PDFs under 25 MB; scanned PDFs without extractable text need OCR, which is not included. The default setup is single-tenant and has no login, so the maker advises against public exposure without authentication or network restrictions. It runs locally or on documented hosting platforms, with persistent storage needed across redeploys.