菜单
Generate spoken MP3 audio from text or Markdown with Gemini TTS. Use for narration, accessibility audio, voice previews, or reading a document aloud with a selected voice, pace, and delivery style.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Restate the previous response plainly and concisely. Use only when the user explicitly asks for a simpler human explanation or invokes bro.
Apply correct-by-construction TypeScript engineering standards covering boundary parsing, typed failures, domain modeling, module boundaries, dependency injection, testing, and type safety. Use when writing or reviewing TypeScript.
Audit installed Agent Skills for duplicate copies, unused candidates, oversized descriptions, loaded roots, and prompt-budget pressure. Use when cleaning or debugging skill collections across common agent runtimes.
Apply concrete clarity, concision, structure, grammar, and plain-English checks when editing prose, reviewing drafts, writing reports or articles, or teaching clear writing.
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Produce an implementation-ready technical specification using typed contracts, concrete module boundaries, call stacks, data flows, alternatives, file changes, and vertical red-green test slices. Use when the user asks for a tech spec or architecture handoff.
| name | gemini-tts |
| description | Generate spoken MP3 audio from text or Markdown with Gemini TTS. Use for narration, accessibility audio, voice previews, or reading a document aloud with a selected voice, pace, and delivery style. |
| license | MIT |
| compatibility | Requires Python 3.10+, google-genai 1.65+, ffmpeg, and a Gemini API key. Optional playback needs afplay, ffplay, or mpv. |
Generate an MP3 from inline text or a UTF-8 text/Markdown file with the bundled script.
Resolve paths relative to this SKILL.md; do not assume a particular install directory.
python3 -m pip install -r <skill-directory>/requirements.txt
export GEMINI_API_KEY='...'
GOOGLE_API_KEY and OPENCODE_GOOGLE_API_KEY are accepted as fallbacks. Set GEMINI_TTS_MODEL to override the default model.
Confirm or infer:
For long input, report the chunk count before making paid API calls. Ask for confirmation when the request is unexpectedly large or the user has not clearly approved generation.
python3 <skill-directory>/scripts/generate_tts.py --list-voices
python3 <skill-directory>/scripts/generate_tts.py --list-templates
python3 <skill-directory>/scripts/generate_tts.py --show-template mystery-narrator
Bundled templates include mystery-narrator, newscaster, whisper, empathetic, deadpan, promo-hype, and podcast-newsletter.
From text:
python3 <skill-directory>/scripts/generate_tts.py \
--text 'Read this clearly and naturally.' \
--voice Orus \
--output ./narration.mp3
From a file and template:
python3 <skill-directory>/scripts/generate_tts.py \
--file ./article.md \
--template podcast-newsletter \
--output ./article.mp3 \
--play
Customize delivery when needed:
python3 <skill-directory>/scripts/generate_tts.py \
--file ./script.txt \
--voice Kore \
--profile 'Calm technical narrator' \
--scene 'A quiet recording booth' \
--notes 'Clear diction, measured pace, neutral accent' \
--speed 1.1 \
--output ./script.mp3
Explicit CLI flags override template values. Templates override the hard defaults (Orus, speed 1.0).
--max-workers N: concurrent chunk requests; default 1--requests-per-minute N: request throttle; default 8; 0 disables it--allow-partial: write an MP3 despite failed chunks; avoid unless the user accepts missing audioEnvironment equivalents are GEMINI_TTS_MAX_WORKERS and GEMINI_TTS_RPM.
After generation:
Never print API keys or include them in command examples, logs, or output files.