Sprep vs UNESCO PDF-to-Podcast
Sprep
sprep.chUNESCO PDF-to-Podcast
github.comSide by side
| Figure | Sprep | UNESCO PDF-to-Podcast |
|---|---|---|
| Price from | $36/mo | — |
| Free plan | Yes | — |
| Free trial | — | — |
| Open source | — | — |
| Web | Yes | — |
| Windows | — | Yes |
| macOS | — | Yes |
| Linux | — | Yes |
| Self-hosted | — | Yes |
| Plans published | 4 | 0 |
| Spec score · AI Podcast Generators | 7.6 (#10) | 7.2 (#21) |
| Languages | Sprep says it generates audio in more than 70 languages from a validated master script. | The project supports script generation in UNESCO’s six official languages: English, French, Chinese, Spanish, Arabic, and Russian. |
| Purpose | Sprep turns uploaded documents such as PDFs, presentations, and articles into editable AI-generated podcasts. | The project converts scientific PDFs into podcast-style audio conversations using AI. |
| Security | The company says Enterprise customers can choose Swiss hosting, SSO, and dedicated infrastructure, and describes the service as GDPR compliant. | The README describes a local Ollama-based script-generation setup and makes no specific security certification or compliance claim. |
Plans
In their own words
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.