Blog AudioSAFE

Claude Code blog skill suite: 30 sub-skills, 5 agents, 5-gate v1.9.0 Blog Delivery Contract, dual-optimized for Google rankings and AI citations. Active development at AI-Marketing-Hub/claude-blog (AI Marketing Hub Pro community); public releases ship here.

The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.

---
name: blog-audio
description: >
  Generate audio narration of blog posts using Google Gemini TTS.
  Supports summary narration, full article read-aloud, and two-speaker
  podcast/dialogue mode with 30 voice options. Outputs MP3 with HTML5
  audio embed code. Works standalone via /blog audio or internally from
  blog-write. Falls back gracefully when API key is not configured.
  Use when user says "blog audio", "narrate blog", "audio version",
  "text to speech", "tts", "podcast mode", "read aloud", "audio narration",
  "voice", "narration", "generate audio".
user-invokable: true
argument-hint: "[generate|voices|setup] [file-or-text] [--mode summary|full|dialogue] [--voice name]"
license: MIT
metadata:
  author: AgriciDaniel
  version: "2.2.0"
---

# Blog Audio: Gemini TTS Narration for Blog Posts

Generate professional audio narration of blog content using Google's Gemini TTS.
Three modes: summary (200-300 word spoken overview), full article read-aloud,
or two-speaker podcast dialogue. 30 voices, 80+ languages, HTML5 embed output.

## Quick Reference

| Command | What it does |
|---------|-------------|
| `/blog audio generate <file>` | Generate audio narration of a blog post |
| `/blog audio voices` | Show available voices with characteristics |
| `/blog audio setup` | Check/configure API key for Gemini TTS |

## Prerequisites

- Python 3.11+ (venv managed automatically by `run.py`)
- `GOOGLE_AI_API_KEY` environment variable (same key used by blog-image)
- FFmpeg (for WAV-to-MP3 conversion; falls back to WAV if missing)

## Always Use run.py Wrapper

```bash
# CORRECT:
python3 scripts/run.py generate_audio.py --text "..." --voice Charon --json

# WRONG:
python3 scripts/generate_audio.py --text "..."  # Fails without venv
```

## API Key Check (Gate Pattern)

Before generating audio, check for the API key:

```bash
test -n "${GOOGLE_AI_API_KEY:-}" && echo "GOOGLE_AI_API_KEY is set" || echo "GOOGLE_AI_API_KEY is not set"
```

- If set: proceed with generation
- If not set: guide the user:
  "Audio generation requires a Google AI API key. Get one free at https://aistudio.google.com/apikey
   Then set it: `export GOOGLE_AI_API_KEY=your-key`
   This can be the same key used by `/blog image`, but it must be exported in the shell."
- **When called internally** (from blog-write): return silently if key is missing.
  Never block the writing workflow.

## Setup

For `/blog audio setup`:

1. Check if `GOOGLE_AI_API_KEY` is set in environment
2. If blog-image uses project `.mcp.json`, confirm the referenced env var is exported
3. If not, guide user to https://aistudio.google.com/apikey
4. Verify with a dry run: `python3 scripts/run.py generate_audio.py --text "Test" --dry-run --json`

## Voice Selection

For `/blog audio voices`:

Load `references/voices.md` and present the voice catalog to the user.

Ask the user which voice they prefer, or recommend based on content type:
- **Article narration**: Charon (Informative) or Sadaltager (Knowledgeable)
- **Tutorial/how-to**: Achird (Friendly) or Sulafat (Warm)
- **News/analysis**: Rasalgethi (Informative) or Schedar (Even)
- **Lifestyle/wellness**: Aoede (Breezy) or Vindemiatrix (Gentle)
- **Dialogue host**: Puck (Upbeat) or Laomedeia (Upbeat)
- **Dialogue expert**: Kore (Firm) or Charon (Informative)

## Generation Workflow

For `/blog audio generate <file>`:

### Step 1: Read the Blog Post

Read the file and extract:
- Title (from H1 or frontmatter)
- Full content (markdown body)
- Approximate word count

### Step 2: Choose Mode

Ask the user (or auto-select if they specified `--mode`):

| Mode | When to use | Output |
|------|-------------|--------|
| **Summary** | Quick audio overview (1-2 min) | 200-300 word spoken summary |
| **Full** | Complete read-aloud (5-15 min) | Full article as natural speech |
| **Dialogue** | Podcast-style (3-8 min) | Two-person conversation about the article |

### Step 3: Prepare Text

Claude prepares the text; the script does TTS only.

**Summary mode:**
Write a 200-300 word spoken summary of the article. Rules:
- Write as natural speech, not written text
- Open with the article's key finding or answer
- Cover 3-5 main takeaways
- Close with actionable advice
- No markdown, no "In this article...", no meta-commentary
- Use conversational transitions ("Here's what matters...", "The key finding is...")

**Full mode:**
Strip the markdown content to clean spoken text:
- Headings become natural transitions ("Next, let's look at...")
- Links become plain text (remove URLs, keep anchor text)
- Images and charts: omit or briefly describe ("As the data shows...")
- Code blocks: describe verbally ("The code uses a for-loop to...")
- Lists: convert to natural sentences
- Remove frontmatter, schema markup, HTML tags
- Add brief intro: "This is [title], published on [date]."

**Dialogue mode:**
Write a 2-person conversation script about the article:
- Speaker1 = Host (curious, asks good questions)
- Speaker2 = Expert (knowledgeable, gives clear answers)
- Format each line as: `Speaker1: What's the key takeaway here?`
- Cover the article's main points conversationally
- 15-25 exchanges (produces ~3-8 minutes)
- Natural, not stilted ("That's a great point" over "Indeed, as the research indicates")

### Step 4: Select Voice

If the user chose a voice, use it. Otherwise, recommend based on mode:
- Summary/Full: default to Charon (Informative)
- Dialogue: default to Puck (Host) + Kore (Expert)

### Step 5: Generate Audio

Write the prepared text to a file under the working directory, then call:

```bash
# Single voice (summary or full mode)
python3 scripts/run.py generate_audio.py \
  --text-file blog_audio_prepared.txt \
  --voice Charon \
  --model flash \
  --output audio/post-slug.mp3 \
  --json

# Two voices (dialogue mode)
python3 scripts/run.py generate_audio.py \
  --text-file blog_audio_dialogue.txt \
  --voice Puck \
  --voice2 Kore \
  --model pro \
  --output audio/post-slug-dialogue.mp3 \
  --json
```

**Model selectio

SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.

What the source does

Filesystem

none-observed

Network

none-observed

Shell

none-observed

Dependencies

not all pinned

Secrets in source

none-found

Findings (2)

return base64.b64decode(data)

google-genai

Gates applied: no_behavioural_pass.