Audify vs UNESCO PDF-to-Podcast
Audify
github.comUNESCO PDF-to-Podcast
github.comSide by side
| Figure | Audify | UNESCO PDF-to-Podcast |
|---|---|---|
| Price from | — | — |
| Free plan | — | — |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | — |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | — | Yes |
| API | Yes | — |
| Self-hosted | Yes | Yes |
| Plans published | 0 | 0 |
| Spec score · AI Podcast Generators | 7.7 (#8) | 7.2 (#21) |
| Integrations | The documented external providers are Ollama for local model inference and OpenAI for TTS and optional LLM fallback. | The documented pipeline uses Docling for PDF extraction, Ollama with Granite4 for script generation, and VibeVoice for audio synthesis. |
| License | The repository is licensed under the MIT License. | The repository’s LICENSE file identifies the project license as MIT. |
| Purpose | Audify converts PDF, DOC, and DOCX documents into editable two-speaker podcast scripts and downloadable MP3 audio. | The project converts scientific PDFs into podcast-style audio conversations using AI. |
| Requirements | The setup instructions require Docker Engine 24.x or later and Docker Compose Plugin v2 or later; an OpenAI API key is required for TTS, while Ollama is optional. | The README lists Python 3.9 or newer, Poetry, and Ollama as prerequisites, and recommends a GPU while allowing CPU fallback. |
| Security | The maker says Audify lacks production-grade security controls and requires a security review before production use. | The README describes a local Ollama-based script-generation setup and makes no specific security certification or compliance claim. |
In their own words
Audify
Audify is a free, open-source application that turns PDF, DOC and DOCX files into editable two-speaker podcast scripts and downloadable MP3 episodes. It extracts document text and can use OCR when a scanned PDF yields little text. Users review and revise speaker turns, wording and flow, choose host and guest voices, and select conversational, educational or professional tones before generating audio. Ollama is the primary script-generation route, with OpenAI as a fallback; an OpenAI API key is required for text-to-speech, while Ollama is optional. The TTS service creates speech for dialogue turns, combines it into MP3, and supports playback and download. Audify uses FastAPI microservices with a React and Vite frontend and is orchestrated for local Docker Compose deployment. Its API handles uploads, generation, job status and downloads. Docker Engine 24.x or later and Docker Compose Plugin v2 or later are required. Uploads are limited to 10 MB, and jobs reset after container restarts unless storage is added.
UNESCO PDF-to-Podcast
UNESCO PDF-to-Podcast turns scientific PDFs into podcast-style conversations. Its pipeline extracts structured material with Docling, uses Ollama with Granite4 to draft a dialogue, then creates audio with VibeVoice. Scripts can target experts, the general public, young people, or novices, and can be generated in English, French, Chinese, Spanish, Arabic, or Russian. Included native voices are available for English and Chinese; for the other four languages, English voices are used unless users provide samples. Users can set the desired duration and choose two to four speakers; defaults are 10 minutes and two speakers. The open-source project is free under the MIT license and can run locally from the command line on Linux, macOS, Windows, or self-hosted setups. Installation requires Python 3.9 or later, Poetry, and Ollama. A GPU is recommended, though CPU use is possible. It currently accepts one PDF at a time, and lengthy documents may need to be split into chunks. Audio generation can demand substantial GPU memory, particularly with the 7B model.