Update README.md
Browse files
README.md
CHANGED
@@ -13,5 +13,26 @@ license: mit
|
|
13 |
thumbnail: >-
|
14 |
https://cdn-uploads.huggingface.co/production/uploads/66cf41ae75a88154445c1144/7M0CYMVuVC0Xf1ZqxCyo_.png
|
15 |
---
|
|
|
16 |
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
thumbnail: >-
|
14 |
https://cdn-uploads.huggingface.co/production/uploads/66cf41ae75a88154445c1144/7M0CYMVuVC0Xf1ZqxCyo_.png
|
15 |
---
|
16 |
+
[Project Overview Video](https://www.canva.com/design/DAGp9q0Pr_I/3XZlutt5Zwhn_tsPN3vZiA/watch?utm_content=DAGp9q0Pr_I&utm_campaign=designshare&utm_medium=link2&utm_source=uniquelinks&utlId=h0d38006656)
|
17 |
|
18 |
+
Narrated Slideshow Generator
|
19 |
+
AI-powered tool that converts any topic into a narrated slideshow with generated images and audio.
|
20 |
+
|
21 |
+
Install dependencies:
|
22 |
+
pip install gradio google-genai python-dotenv pillow deepgram-sdk
|
23 |
+
|
24 |
+
Set up API keys in .env:
|
25 |
+
GEMINI_KEY=your_gemini_api_key
|
26 |
+
DEEPGRAM_KEY=your_deepgram_key # optional
|
27 |
+
|
28 |
+
Run:
|
29 |
+
python app.py
|
30 |
+
|
31 |
+
Use:
|
32 |
+
Enter a topic, click Generate, navigate with Previous/Next buttons.
|
33 |
+
|
34 |
+
How it Works
|
35 |
+
Gemini 2.5 generates slide content and speaker notes
|
36 |
+
Gemini TTS creates audio narration
|
37 |
+
Imagen 3 generates slide images
|
38 |
+
Gradio provides the web interface
|