blog-audio

1# Blog Audio: Gemini TTS Narration for Blog Posts
2 
3Bundled paths below use host Markdown substitution of `${CLAUDE_SKILL_DIR}`;
4it is not an exported shell variable. Resolve them before execution, quote
5paths, and refuse nonabsolute overrides. Pass `blog_reference_root` resolved
6from `${CLAUDE_SKILL_DIR}/../blog/references`, `blog_template_root` from
7`${CLAUDE_SKILL_DIR}/../blog/templates`, and needed sibling roots to agents.
8Read the main reference `orchestration-details.md` before loading project
9context; pass only its helper-fenced output to downstream agents.
10 
11Generate professional audio narration of blog content using Google's Gemini TTS.
12Three modes: summary (200-300 word spoken overview), full article read-aloud,
13or two-speaker podcast dialogue. 30 prebuilt voices, over 130 languages on
14Gemini 3.8 Flash TTS (over 100 on Flash-Lite), HTML5 embed output. Dated model,
15pricing and language facts live in `${CLAUDE_SKILL_DIR}/references/models.md`.
16 
17## Cost and consent gate (mandatory, read first)
18 
19This skill spends the user's Google AI credit and writes audio files.
20 
21- **What it spends:** one paid Gemini TTS call per text chunk. Long text is
22  split into chunks, so a full read-aloud costs several calls. The script's
23  `--max-chunks` flag caps the chunks per run (default 12); never raise it
24  without telling the user the new worst-case cost.
25- **Cost basis:** audio output tokens at 25 tokens per second of audio, priced
26…