blog-audio

Name: blog-audio
Author: AgriciDaniel

1.3kinstalls251forks

How to install blog-audio?

agricidaniel/claude-blog/blog-audio

$npx -y skills add AgriciDaniel/claude-blog --skill blog-audio

Installs into the current project.

Summary

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-writ

Files · 1

View on GitHub

SKILL.md

1	# Blog Audio: Gemini TTS Narration for Blog Posts
2
3	Generate professional audio narration of blog content using Google's Gemini TTS.
4	Three modes: summary (200-300 word spoken overview), full article read-aloud,
5	or two-speaker podcast dialogue. 30 voices, 80+ languages, HTML5 embed output.
6
7	## Quick Reference
8
9	\| Command \| What it does \|
10	\|---------\|-------------\|
11	\| `/blog audio generate <file>` \| Generate audio narration of a blog post \|
12	\| `/blog audio voices` \| Show available voices with characteristics \|
13	\| `/blog audio setup` \| Check/configure API key for Gemini TTS \|
14
15	## Prerequisites
16
17	- Python 3.11+ (venv managed automatically by `run.py`)
18	- `GOOGLE_AI_API_KEY` environment variable (same key used by blog-image)
19	- FFmpeg (for WAV-to-MP3 conversion; falls back to WAV if missing)
20
21	## Always Use run.py Wrapper
22
23	```bash
24	# CORRECT:
25	python3 scripts/run.py generate_audio.py --text "..." --voice Charon --json
26
27	# WRONG:
28	python3 scripts/generate_audio.py --text "..." # Fails without venv
29	```
30
31	## API Key Check (Gate Pattern)
32
33	Before generating audio, check for the API key:
34
35	```bash
36	echo $GOOGLE_AI_API_KEY
37	```
38
39	- If set: proceed with generation
40	- If not set: guide the user:
41	"Audio generation requires a Google AI API key. Get one free at https://aistudio.google.com/apikey
42	Then set it: `export GOOGLE_AI_API_KEY=your-key`
43	This is the same key used by `/blog image`: if image generation works, audio works too."
44	- When called internally (from blog-write): return silently if key is missing.
45	Never block the writing workflow.
46
47	## Setup
48
49	For `/blog audio setup`:
50
51	1. Check if `GOOGLE_AI_API_KEY` is set in environment
52	2. If blog-image is configured (check `.mcp.json`), the key is already available
53	3. If not, guide user to https://aistudio.google.com/apikey
54	4. Verify with a dry run: `python3 scripts/run.py generate_audio.py --text "Test" --dry-run --json`
55
56	## Voice Selection
57
58	For `/blog audio voices`:
59
60	Load `references/voices.md` and present the voice catalog to the user.
61
62	Ask the user which voice they prefer, or recommend based on content type:
63	- Article narration: Charon (Informative) or Sadaltager (Knowledgeable)
64	- Tutorial/how-to: Achird (Friendly) or Sulafat (Warm)
65	- News/analysis: Rasalgethi (Informative) or Schedar (Even)
66	- Lifestyle/wellness: Aoede (Breezy) or Vindemiatrix (Gentle)
67	- Dialogue host: Puck (Upbeat) or Laomedeia (Upbeat)
68	- Dialogue expert: Kore (Firm) or Charon (Informative)
69
70	## Generation Workflow
71
72	For `/blog audio generate <file>`:
73
74	### Step 1: Read the Blog Post
75
76	Read the file and extract:
77	- Title (from H1 or frontmatter)
78	- Full content (markdown body)
79	- Approximate word count
80
81	### Step 2: Choose Mode
82
83	Ask the user (or auto-select if they specified `--mode`):
84
85	\| Mode \| When to use \| Output \|
86	\|------\|-------------\|--------\|
87	\| Summary \| Quick audio overview (1-2 min) \| 200-300 word spoken summary \|
88	\| Full \| Complete read-aloud (5-15 min) \| Full article as natural speech \|
89	\| Dialogue \| Podcast-style (3-8 min) \| Two-person conversation about the article \|
90
91	### Step 3: Prepare Text
92
93	CRITICAL: Claude prepares the text. The script does TTS only.
94
95	Summary mode:
96	Write a 200-300 word spoken summary of the article. Rules:
97	- Write as natural speech, not written text
98	- Open with the article's key finding or answer
99	- Cover 3-5 main takeaways
100	- Close with actionable advice
101	- No markdown, no "In this article...", no meta-commentary
102	- Use conversational transitions ("Here's what matters...", "The key finding is...")
103
104	Full mode:
105	Strip the markdown content to clean spoken text:
106	- Headings become natural transitions ("Next, let's look at...")
107	- Links become plain text (remove URLs, keep anchor text)
108	- Images and charts: omit or briefly describe ("As the data shows...")
109	- Code blocks: describe verbally ("The code uses a for-loop to...")
110	- Lists: convert to natural sentences
111	- Remove frontmatter, schema markup, HTML tags
112	- Add brief intro: "This is [title], published on [date]."
113
114	Dialogue mode:
115	Write a 2-person conversation script about the article:
116	- Speaker1 = Host (curious, asks good questions)
117	- Speaker2 = Expert (knowledgeable, gives clear answers)
118	- Format each line as: `[Speaker1] What's the key takeaway here?

People who liked this also viewed

6 picks

Type

blog-audio

1.3kinstalls251forks

View on GitHub

How to install blog-audio?

agricidaniel/claude-blog/blog-audio

$npx -y skills add AgriciDaniel/claude-blog --skill blog-audio

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Blog Audio: Gemini TTS Narration for Blog Posts
2
3	Generate professional audio narration of blog content using Google's Gemini TTS.
4	Three modes: summary (200-300 word spoken overview), full article read-aloud,
5	or two-speaker podcast dialogue. 30 voices, 80+ languages, HTML5 embed output.
6
7	## Quick Reference
8
9	\| Command \| What it does \|
10	\|---------\|-------------\|
11	\| `/blog audio generate <file>` \| Generate audio narration of a blog post \|
12	\| `/blog audio voices` \| Show available voices with characteristics \|
13	\| `/blog audio setup` \| Check/configure API key for Gemini TTS \|
14
15	## Prerequisites
16
17	- Python 3.11+ (venv managed automatically by `run.py`)
18	- `GOOGLE_AI_API_KEY` environment variable (same key used by blog-image)
19	- FFmpeg (for WAV-to-MP3 conversion; falls back to WAV if missing)
20
21	## Always Use run.py Wrapper
22
23	```bash
24	# CORRECT:
25	python3 scripts/run.py generate_audio.py --text "..." --voice Charon --json
26
27	# WRONG:
28	python3 scripts/generate_audio.py --text "..." # Fails without venv
29	```
30
31	## API Key Check (Gate Pattern)
32
33	Before generating audio, check for the API key:
34
35	```bash
36	echo $GOOGLE_AI_API_KEY
37	```
38
39	- If set: proceed with generation
40	- If not set: guide the user:
41	"Audio generation requires a Google AI API key. Get one free at https://aistudio.google.com/apikey
42	Then set it: `export GOOGLE_AI_API_KEY=your-key`
43	This is the same key used by `/blog image`: if image generation works, audio works too."
44	- When called internally (from blog-write): return silently if key is missing.
45	Never block the writing workflow.
46
47	## Setup
48
49	For `/blog audio setup`:
50
51	1. Check if `GOOGLE_AI_API_KEY` is set in environment
52	2. If blog-image is configured (check `.mcp.json`), the key is already available
53	3. If not, guide user to https://aistudio.google.com/apikey
54	4. Verify with a dry run: `python3 scripts/run.py generate_audio.py --text "Test" --dry-run --json`
55
56	## Voice Selection
57
58	For `/blog audio voices`:
59
60	Load `references/voices.md` and present the voice catalog to the user.
61
62	Ask the user which voice they prefer, or recommend based on content type:
63	- Article narration: Charon (Informative) or Sadaltager (Knowledgeable)
64	- Tutorial/how-to: Achird (Friendly) or Sulafat (Warm)
65	- News/analysis: Rasalgethi (Informative) or Schedar (Even)
66	- Lifestyle/wellness: Aoede (Breezy) or Vindemiatrix (Gentle)
67	- Dialogue host: Puck (Upbeat) or Laomedeia (Upbeat)
68	- Dialogue expert: Kore (Firm) or Charon (Informative)
69
70	## Generation Workflow
71
72	For `/blog audio generate <file>`:
73
74	### Step 1: Read the Blog Post
75
76	Read the file and extract:
77	- Title (from H1 or frontmatter)
78	- Full content (markdown body)
79	- Approximate word count
80
81	### Step 2: Choose Mode
82
83	Ask the user (or auto-select if they specified `--mode`):
84
85	\| Mode \| When to use \| Output \|
86	\|------\|-------------\|--------\|
87	\| Summary \| Quick audio overview (1-2 min) \| 200-300 word spoken summary \|
88	\| Full \| Complete read-aloud (5-15 min) \| Full article as natural speech \|
89	\| Dialogue \| Podcast-style (3-8 min) \| Two-person conversation about the article \|
90
91	### Step 3: Prepare Text
92
93	CRITICAL: Claude prepares the text. The script does TTS only.
94
95	Summary mode:
96	Write a 200-300 word spoken summary of the article. Rules:
97	- Write as natural speech, not written text
98	- Open with the article's key finding or answer
99	- Cover 3-5 main takeaways
100	- Close with actionable advice
101	- No markdown, no "In this article...", no meta-commentary
102	- Use conversational transitions ("Here's what matters...", "The key finding is...")
103
104	Full mode:
105	Strip the markdown content to clean spoken text:
106	- Headings become natural transitions ("Next, let's look at...")
107	- Links become plain text (remove URLs, keep anchor text)
108	- Images and charts: omit or briefly describe ("As the data shows...")
109	- Code blocks: describe verbally ("The code uses a for-loop to...")
110	- Lists: convert to natural sentences
111	- Remove frontmatter, schema markup, HTML tags
112	- Add brief intro: "This is [title], published on [date]."
113
114	Dialogue mode:
115	Write a 2-person conversation script about the article:
116	- Speaker1 = Host (curious, asks good questions)
117	- Speaker2 = Expert (knowledgeable, gives clear answers)
118	- Format each line as: `[Speaker1] What's the key takeaway here?

People who liked this also viewed

6 picks

Type