podcast

# Podcast Discovery & Generation

Automated end-to-end podcast production pipeline. Discovers trending topics from configurable sources, researches them deeply, generates fact-checked scripts with citations, and produces audio via ElevenLabs TTS.

## Triggers

Use this skill when user asks to:
- "Generate a podcast"
- "Make a podcast episode"
- "Discover podcast topics"
- "Create an audio episode about X"
- "Find topics for podcast"
- "Research and script a podcast"
- "Produce a podcast episode"

## Quick Start

### 1. Configure
```bash
cd ~/.openclaw/skills/podcast
cp config.example.yaml config.yaml
# Edit config.yaml: add sources, interests, voice, storage
```

### 2. Discover Topics
```bash
python3 scripts/discover.py --config config.yaml --limit 10
```

### 3. Run Pipeline
```bash
python3 scripts/pipeline.py --config config.yaml --topic "Your Topic" --mode manual
```

## Configuration

**Minimal config.yaml:**
```yaml
sources:
  - type: rss
    url: https://aeon.co/feed.rss
    name: Aeon
  - type: hackernews
    min_points: 200

interests:
  - AI/Tech
  - Science

voice:
  voice_id: "<your-voice-id>"

storage:
  type: local
  path: ./output
```

**Storage options:**
- `type: s3` — Upload to S3 (requires bucket, region)
- `type: local` — Save to local directory

## Pipeline Stages

1. **Discovery** — Fetch and rank topics from sources
2. **Research** — Web search framework (OpenClaw worker populates)
3. **Script** — Generate script with LLM, enforce `[Source: URL]` citations
4. **Verify** — Cross-check claims against research sources
5. **Audio** — Strip citations, call ElevenLabs TTS
6. **Upload** — Save to S3 or local storage

Each stage can run standalone or as full pipeline.

## Usage Examples

**Discover only:**
```bash
python3 scripts/discover.py --config config.yaml --limit 5 --output topics.json
```

**Full pipeline (auto mode):**
```bash
python3 scripts/pipeline.py --config config.yaml --mode auto
```

**Specific topic:**
```bash
python3 scripts/pipelin...

# Podcast Discovery & Generation Skill

Automated podcast topic discovery, research, script generation, fact-checking, and audio production using AI. Clean, configurable, open-source pipeline built for OpenClaw.

## Features

- 🔍 **Multi-Source Discovery**: Fetch topics from RSS feeds, Hacker News, Nature, and more
- 🧠 **Smart Ranking**: Prioritize topics by your interests using keyword matching
- 📚 **Deep Research**: Structure for web research with source verification
- ✍️ **Script Generation**: LLM-powered script writing with citation enforcement
- ✅ **Fact Verification**: Cross-reference claims against research sources
- 🎙️ **Audio Production**: ElevenLabs TTS with citation stripping
- ☁️ **Flexible Storage**: S3 or local file storage
- 📦 **Delivery-ready**: Designed to plug into your own delivery channel (WhatsApp/SMS/email) via a worker

## Quick Start

### 1. Install

```bash
# Install via ClawHub (recommended)
clawhub install podcast

# Or manual install
cd ~/.openclaw/skills/
git clone <repo-url> podcast
cd podcast
```

### 2. Configure

```bash
cp config.example.yaml config.yaml
# Edit config.yaml with your settings
```

**Required config:**
- `sources`: List of RSS feeds and built-in sources
- `interests`: Your topic preferences (keywords)
- `voice.voice_id`: Your ElevenLabs voice ID
- `storage.type`: `s3` or `local`

**For S3 storage:**
- `storage.bucket`: S3 bucket name
- `storage.region`: AWS region
- Ensure AWS credentials are configured (`aws configure`)

### 3. Discover Topics

```bash
python3 scripts/discover.py --config config.yaml --limit 10 --output discovery.json
```

This scans all configured sources and outputs a ranked list of topics.

### 4. Run Full Pipeline (Manual Mode)

```bash
python3 scripts/pipeline.py --config config.yaml --mode manual
```

Or specify a topic directly:

```bash
python3 scripts/pipeline.py --config config.yaml --topic "AI Reasoning Models" --mode manual
```

**Manual mode** pauses after each stage so you can revi...