synthesize

synthesize is a skill for Claude Code from terrylica/cc-skills. It costs 38 tokens per session (782 once invoked), scanned A, original, MIT.

A text-to-speech tool that turns written text into a WAV audio file using Kokoro TTS. Text-to-speech means generating spoken audio from written words.

In plain words
What is it for?
Use it to create spoken versions of text, choose a voice and language, adjust speaking speed, and save the result as a WAV file.
Why use it?
It removes the need to record the speech yourself or use a separate audio editor for basic voice generation. Long text can also be processed in chunks.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the kokoro-tts plugin — 5 skills shipped together , and of cc-skills

Good fit Use it to create spoken versions of text, choose a voice and language, adjust speaking speed, and save the result as a WAV file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/terrylica/cc-skills/synthesize
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add terrylica/cc-skills --skill synthesize
Clone the repo
git clone --depth 1 https://github.com/terrylica/cc-skills

Made for: Claude Code.

Or install kokoro-tts, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for synthesize

README.md
[![agentmods](https://agentmods.dev/badge/skills/terrylica/cc-skills/synthesize/github.svg)](https://agentmods.dev/skills/terrylica/cc-skills/synthesize)
Your own site
<a href="https://agentmods.dev/skills/terrylica/cc-skills/synthesize"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/synthesize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for synthesize

Your own site · 80×15
<a href="https://agentmods.dev/skills/terrylica/cc-skills/synthesize"><img src="https://agentmods.dev/badge/skills/terrylica/cc-skills/synthesize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 782 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 76
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00038 $0.00782
Opus 5 $0.00019 $0.00391
Sonnet 5 $0.00008 $0.00156
Haiku 4.5 $0.00004 $0.00078

Measured 5d ago against content hash dd0a832e5ba7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

synthesize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/kokoro-tts/skills/synthesize/SKILL.md · 79 lines

How it starts

The opening of the file, as written. The whole thing — 79 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Synthesize Speech

Generate speech from text using the Kokoro TTS CLI tool. Supports single WAV output or chunked streaming for long text.

Self-Evolving Skill: This skill improves through use. If instructions are wrong, parameters drifted, or a workaround was needed — fix this file immediately, don't defer. Only update for real, reproducible issues.

Quick Usage

# Single WAV
~/.local/share/kokoro/.venv/bin/python ~/.local/share/kokoro/tts_generate.py \
  --text "Hello from Kokoro TTS" --voice af_heart --lang en-us --speed 1.0 \
  --output /tmp/kokoro-tts-$$.wav

# Play it
afplay /tmp/kokoro-tts-$$.wav

Parameters

Parameter Default Description
--text (required) Text to synthesize
--voice af_heart Voice name (see voice catalog)
--lang en-us Language code (en-us, zh, ja, etc.)
--speed 1.0 Speech speed multiplier
--output (required) Output WAV path
--chunk off Chunked streaming mode for long text

Voice Catalog

See Voice Catalog for all available voices with quality grades.

Top voices:

Voice ID Name Grade Gender
af_heart Heart A Female
af_bella Bella A- Female
af_nicole Nicole B- Female

Chunked Streaming

For long text, use --chunk to get progressive playback:

~/.local/share/kokoro/.venv/bin/python ~/.local/share/kokoro/tts_generate.py \
  --text "Long text here..." --voice af_heart --lang en-us --speed 1.0 \
  --output /tmp/kokoro-tts-$$.wav --chunk

Each chunk WAV path is printed to stdout as it becomes ready. The final line is DONE <ms>.

Troubleshooting

Issue Cause Solution
No audio output Model not loaded Run /kokoro-tts:install first
Empty text error Input was blank Provide non-empty --text
Slow generation First-run warmup Normal — subsequent runs faster

Read the full file on GitHub · 79 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 79 lines · 38 tokens per session scan A dd0a832e5ba7

Subscribe to this mod's changes

synthesize is a skill published in the GitHub repository terrylica/cc-skills (72 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 782 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.