Gemini tts

Skill iurysza/agent-skills/skills/gemini-tts

Shareable skills for clankers

Install

npx -y skills add iurysza/agent-skills --skill gemini-tts

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

19 days oldThe repository was created 19 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Generates spoken MP3 audio from text or Markdown with Gemini TTS. Use for narration, accessibility, voice previews, or reading documents aloud.

SKILL.md

2.9 KB, as published. Nobody here has run it

Gemini TTS

Generate an MP3 from inline text or a UTF-8 text/Markdown file with the bundled script.

Setup

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.

Before generation

Confirm or infer:

source text or file
output path
voice or template
desired delivery notes and speed
whether playback is wanted

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.

Discover voices and templates

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.

Generate audio

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).

Reliability controls

--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 audio

Environment equivalents are GEMINI_TTS_MAX_WORKERS and GEMINI_TTS_RPM.

Verification

After generation:

Confirm the command exited successfully.
Confirm the MP3 exists and is non-empty.
Report the exact output path.
If playback was requested, report when no supported player is installed.

Never print API keys or include them in command examples, logs, or output files.