Skip to content

Commit 2ded1fa

Browse files
committed
Unify Ellipsis showcase page structure to make it mintlify-compliant
1 parent f69d4ca commit 2ded1fa

File tree

1 file changed

+70
-189
lines changed

1 file changed

+70
-189
lines changed

docs/showcase/Ellipsis.mdx

Lines changed: 70 additions & 189 deletions
Original file line numberDiff line numberDiff line change
@@ -1,226 +1,107 @@
1-
# 🎙️ Ellipsis — One Click. Infinite Conversations.
2-
3-
<div align="center">
4-
<img width="513" alt="Screenshot 2025-05-28 at 1 47 50 PM" src="https://github.com/user-attachments/assets/4eae019c-0795-41e5-b693-3c7a91a86e6b" />
5-
</div>
6-
7-
<br></br>
8-
A next-gen podcast generation agent that brings human-like, high-quality audio content to life—on *any* topic, with just **one click**.
9-
Whether it’s **breaking news**, **deep-dive tech explainers**, **movie reviews**, or **post-match sports breakdowns**, ellipsis crafts intelligent podcast episodes that sound like they were created by seasoned hosts in a professional studio.
10-
111
---
12-
13-
## Introduction
14-
15-
### 🚀 What Makes ellipsis Unique?
16-
17-
- **🧠 Intelligent Multi-Speaker Dialogue**
18-
Automatically generates natural, engaging conversations with multiple distinct voices and personalities.
19-
20-
- **📚 Covers *Everything***
21-
From LLM architectures to lunar eclipses, ellipsis understands the depth and nuance of any topic.
22-
23-
- **✅ Custom Evaluation Engine**
24-
Each episode is passed through rigorous evaluation pipelines to ensure:
25-
- Factual accuracy 🧾
26-
- Legal and ethical soundness ⚖️
27-
- High conversational quality 🎧
28-
2+
title: Ellipsis | One-Click Podcast Generation Agent
3+
description: A next-gen podcast generation agent that brings human-like, high-quality audio content to life on any topic with just one click
4+
sidebar_position: 10
5+
keywords: [ellipsis, podcast, audio, generation, TTS, perplexity, multi-speaker, AI]
296
---
307

31-
## Feature Comparison
32-
33-
| Feature | Ellipsis | NotebookLM | NoteGPT |
34-
|---------------------------------|----------------------------------------------------|----------------------------------------------|----------------------------------------------------|
35-
| 🎙️ Podcast Generation | ✅ fully automated | ✅ fully automated | ✅ fully automated |
36-
| 🧠 Multi-Speaker Support | ✅ Multiple distinct voices | ❌ Two-speaker conversations | ✅ Multiple distinct voices |
37-
| 📚 Topic Versatility | ✅ Covers news, tech, movies, sports, etc. | ⚠️ No web search capability yet | ⚠️ Limited to provided notebook context |
38-
| ✅ Factual & Legal Evaluation | ✅ Built-in evaluators for accuracy & legality | ⚠️ Not Clearly specified | ❌ No evaluation engine |
39-
| 🎧 Audio Output Quality | ✅ Human-like, podcast-ready audio | ✅ Human-like, podcast-ready audio | ❌ Conversations at this point sound more robotic |
40-
| 🛠️ Custom Input formats | ⚠️ Currently working on Documents | ✅ Supports Documents, Video URLs etc | ⚠️ Supports Documents but not other sources |
41-
42-
43-
## Example Usecases
44-
45-
* **Movie Reviews**
46-
47-
48-
https://github.com/user-attachments/assets/824bab23-2aa9-4443-bc87-0ccb013f86fc
8+
**Ellipsis** is a next-generation podcast generation agent that brings human-like, high-quality audio content to life on any topic with just one click. Whether it's breaking news, deep-dive tech explainers, movie reviews, or post-match sports breakdowns, Ellipsis crafts intelligent podcast episodes that sound like they were created by seasoned hosts in a professional studio.
499

10+
## Features
5011

51-
* **Sports News**
52-
53-
54-
https://github.com/user-attachments/assets/c2880157-e577-4997-b108-3771b327e2be
55-
56-
57-
58-
## Tech Stack
59-
60-
* **Backend**: Python, Flask, Redis (pub/sub), llama.cpp, Orpheus TTS
61-
* **Frontend**: React, Vite, Tailwind CSS, Lucide Icons
62-
* **Integration**: Perplexity API, Podbean MCP, Server-Sent Events (SSE)
12+
* **Intelligent Multi-Speaker Dialogue** with multiple distinct voices and personalities
13+
* **Comprehensive Topic Coverage** from LLM architectures to lunar eclipses
14+
* **Custom Evaluation Engine** ensuring factual accuracy, legal compliance, and conversational quality
15+
* **Fully Automated Podcast Generation** with human-like, podcast-ready audio output
16+
* **Real-time Streaming Updates** via Server-Sent Events (SSE)
17+
* **Podbean Integration** for direct podcast publishing
18+
* **Trending Topics Detection** using Perplexity API
6319

6420
## Prerequisites
6521

6622
* Node.js v16+ and npm/yarn
6723
* Python 3.10+ and pip
6824
* Redis server running (default on `localhost:6380`)
25+
* Perplexity API key, Podbean credentials
6926

70-
## Configuration
27+
## Installation
7128

72-
* Copy this to `backend/.env` and set:
29+
```bash
30+
# Clone the repository
31+
git clone https://github.com/dineshkannan010/Ellipsis.git
32+
cd Ellipsis
7333

74-
```ini
75-
REDIS_URL=redis://localhost:6379
76-
PERPLEXITY_API_KEY=your_key_here
77-
PODBEAN_CLIENT_ID=...
78-
PODBEAN_CLIENT_SECRET=...
79-
```
34+
# Backend setup
35+
cd backend
36+
python -m venv venv
37+
source venv/bin/activate # macOS/Linux
38+
pip install -r requirements.txt
8039

81-
* Copy this to `frontend/.env` and set:
40+
# Install native packages
41+
pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
42+
pip install git+https://github.com/freddyaboulton/orpheus-cpp.git
43+
pip install huggingface_hub[hf_xet] hf_xet
8244

83-
```ini
84-
# VCL: default set to localhost
85-
REACT_APP_API_URL=http://127.0.0.1:5000
86-
```
45+
# Frontend setup
46+
cd ../frontend
47+
npm install
48+
```
8749

88-
## Installation
50+
## Configuration
8951

90-
1. **Clone the repo**
52+
Create `backend/.env`:
53+
```ini
54+
REDIS_URL=redis://localhost:6379
55+
PERPLEXITY_API_KEY=your_key_here
56+
PODBEAN_CLIENT_ID=...
57+
PODBEAN_CLIENT_SECRET=...
58+
```
9159

92-
```bash
93-
git clone https://github.com/dineshkannan010/Ellipsis.git
94-
cd Ellipsis
95-
```
60+
Create `frontend/.env`:
61+
```ini
62+
REACT_APP_API_URL=http://127.0.0.1:5000
63+
```
9664

97-
2. **Backend setup**
65+
## Usage
9866

67+
1. **Start Redis Server**:
9968
```bash
100-
cd backend
101-
python -m venv venv
102-
source venv/bin/activate # macOS/Linux
103-
venv\Scripts\activate # Windows
104-
pip install -r requirements.txt
69+
redis-server --port 6380
10570
```
106-
Install native & extra-index packages
107-
Some packages aren’t available on PyPI and must be pulled from alternate indexes or GitHub:
10871

72+
2. **Launch Backend**:
10973
```bash
110-
# llama.cpp (CPU wheel)
111-
pip install llama-cpp-python \
112-
--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
113-
114-
# Orpheus TTS bindings
115-
pip install git+https://github.com/freddyaboulton/orpheus-cpp.git
116-
117-
# HuggingFace XET backend
118-
pip install huggingface_hub[hf_xet] hf_xet
119-
74+
cd backend
75+
python app.py
12076
```
12177

122-
3. **Frontend setup**
123-
78+
3. **Launch Frontend**:
12479
```bash
12580
cd frontend
126-
npm install # or yarn install
81+
npm run dev
12782
```
12883

129-
## Usage
130-
131-
### Content Generation
132-
133-
* Launch backend:
134-
135-
```bash
136-
cd backend
137-
python app.py
138-
```
139-
140-
* Launch Redis Server
141-
142-
```bash
143-
redis-server --port 6380
144-
```
145-
* Launch frontend:
146-
147-
```bash
148-
cd frontend
149-
npm run dev # or yarn dev
150-
```
151-
152-
* Launch Podbean Server
153-
154-
```bash
155-
cd backend/integrations/podbean_mcp
156-
pip install -e .
157-
python server.py
158-
159-
```
160-
* Launch Podbean Client
161-
162-
```bash
163-
cd backend/integrations/podbean_mcp
164-
python client.py server.py
165-
166-
```
167-
168-
* Enter a topic in the homepage textbox and hit **Enter**. Switch to the `ContentGenerationView` to see live script & audio progress.
169-
170-
### Streaming Updates (SSE)
171-
172-
* The frontend subscribes to `/stream` via EventSource.
173-
* Backend publishes events of types `status`, `script`, and `audio`.
174-
175-
### Trending Topics
176-
177-
* Click **Trending** in the post box.
178-
* Fetches `/api/trending`, which queries Perplexity with a custom prompt.
179-
180-
### Podbean Publishing
181-
182-
* After audio is ready, enter a prompt like `Post this podcast to Podbean`.
183-
* The client detects `podbean` intent and calls `/api/podbean/publish` via Beacon or `fetch`.
184-
185-
## 🙏 Acknowledgments
186-
187-
Huge thanks to [amurshak](mailto:[email protected]) for creating and maintaining the Podbean MCP Server.
188-
189-
## License
190-
191-
[MIT © Ellipsis]((https://github.com/dineshkannan010/Ellipsis/blob/master/LICENSE.md))
84+
4. **Optional: Podbean Integration**:
85+
```bash
86+
cd backend/integrations/podbean_mcp
87+
pip install -e .
88+
python server.py
89+
python client.py server.py
90+
```
19291

193-
## Contact
92+
5. **Generate Content**: Enter a topic in the homepage textbox and hit Enter. Switch to `ContentGenerationView` to see live script & audio progress.
19493

195-
For questions or feedback, open an issue or reach out to
94+
## Code Explanation
19695

197-
<table>
198-
<tr>
199-
<td align="center">
200-
<a href="https://github.com/dineshkannan010">
201-
<sub><b>Dinesh Kannan</b></sub>
202-
</a><br />
203-
</td>
204-
<td align="center">
205-
<a href="https://github.com/lohithsowmiyan">
206-
<sub><b>Lohith Senthilkumar</b></sub>
207-
</a><br />
208-
</td>
209-
<td align="center">
210-
<a href="https://github.com/ParinitadasUX">
211-
<sub><b>Parinita Das</b></sub>
212-
</a><br />
213-
</td>
214-
<td align="center">
215-
<a href="https://github.com/manideepika21">
216-
<sub><b>Manideepika Myaka</b></sub>
217-
</a><br />
218-
</td>
219-
</tr>
220-
</table>
96+
* **Backend**: Python Flask with Redis pub/sub, llama.cpp, and Orpheus TTS for audio generation
97+
* **Frontend**: React with Vite, Tailwind CSS, and Server-Sent Events for real-time updates
98+
* **AI Integration**: Perplexity API for content generation and trending topics detection
99+
* **Audio Processing**: Multi-speaker TTS with distinct voice personalities
100+
* **Content Evaluation**: Built-in pipelines for factual accuracy and legal compliance
101+
* **Podcast Publishing**: Direct integration with Podbean via MCP server
221102

222103
## Links
223104

224-
- **[GitHub Repository](https://github.com/dineshkannan010/Ellipsis)** - Full source code
225-
- **[Demo Video](https://www.youtube.com/watch?v=XUPsSuCBTFw)** - Watch it in action
226-
- **[Devpost Submission](https://devpost.com/software/ellipsis)** - Hackathon entry
105+
- [GitHub Repository](https://github.com/dineshkannan010/Ellipsis)
106+
- [Demo Video](https://www.youtube.com/watch?v=XUPsSuCBTFw)
107+
- [Devpost Submission](https://devpost.com/software/ellipsis)

0 commit comments

Comments
 (0)