# Transform any PDF document into an AI-generated audio interview/dialogue

**URL:** <https://discuss.huggingface.co/t/transform-any-pdf-document-into-an-ai-generated-audio-interview-dialogue/105793>\
**Category:** Spaces\
**Created:** [September 7, 2024, 5:53pm UTC](https://discuss.huggingface.co/t/transform-any-pdf-document-into-an-ai-generated-audio-interview-dialogue/105793 "2024-09-07T17:53:18Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![AIPeterWorld](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/aipeterworld/32/30601_2.png) [@AIPeterWorld](https://discuss.huggingface.co/u/AIPeterWorld)\
**Post date:** [September 7, 2024, 5:53pm UTC](https://discuss.huggingface.co/t/transform-any-pdf-document-into-an-ai-generated-audio-interview-dialogue/105793/1 "2024-09-07T17:53:18Z")

</div>

[Doc-To-Dialogue](https://huggingface.co/spaces/AIPeterWorld/Doc-To-Dialogue)

_Transform any PDF document (research report, market analysis, presentations, user guides,…) into an #AI-generated audio interview/dialogue_ with two different AI voices that discuss the most relevant aspects of the document. An alternative way to comprehend and enhance document engagement.

In this personal experiment I used Google Gemini 1.5 Flash #API for document processing, OpenAI Whisper #TTS for the voice generation, Gradio for the user interface. Code uploaded in a Hugging Face Space.

Any repost or feedback will be much appreciated!

> **[Pedro Sanchez Alvarez on LinkedIn: Doc To Dialogue - a Hugging Face Space by...](https://www.linkedin.com/posts/psanchezal_doc-to-dialogue-a-hugging-face-space-by-activity-7233432175650512896-VUum?utm_source=share&utm_medium=member_ios)**
>
> Transform any PDF document (research report, market analysis, presentations, user guides,...) into an #AI-generated audio interview/dialogue with two different…

---

<div class="post-metadata">

**Author:** ![walbertoflores](https://sea2.discourse-cdn.com/hellohellohello/user_avatar/discuss.huggingface.co/walbertoflores/32/32056_2.png) [@walbertoflores](https://discuss.huggingface.co/u/walbertoflores)\
**Post date:** [September 25, 2024, 1:33am UTC](https://discuss.huggingface.co/t/transform-any-pdf-document-into-an-ai-generated-audio-interview-dialogue/105793/2 "2024-09-25T01:33:29Z")

</div>

Wow! Qué genial que ya se puede hacer en español.