tts-init

tts-init is a command for Claude Code from HariFatherKR/claude-qwen-tts. It costs 16 tokens per session (720 once invoked), scanned A, original, MIT.

An interactive setup command for configuring text-to-speech, including the reference voice and default output folder. Text-to-speech means generating spoken audio from written text.

In plain words
What is it for?
Use it after the TTS environment is installed to select a Korean male or female sample, provide a voice file and transcript, and choose where generated audio should be saved.
Why use it?
It removes the need to edit configuration files by hand. It also guides users through choosing a sample voice or registering their own voice recording.

Command for Claude Code

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

Part of the claude-qwen-tts plugin — 1 skill, 5 commands shipped together

Good fit Use it after the TTS environment is installed to select a Korean male or female sample, provide a voice file and transcript, and choose where generated audio should be saved.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/harifatherkr/claude-qwen-tts/tts-init
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.

Clone the repo
git clone --depth 1 https://github.com/HariFatherKR/claude-qwen-tts

Made for: Claude Code.

Or install claude-qwen-tts, the plugin that ships this one along with the rest of its 1 skill, 5 commands.

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 tts-init

README.md
[![agentmods](https://agentmods.dev/badge/commands/harifatherkr/claude-qwen-tts/tts-init/github.svg)](https://agentmods.dev/commands/harifatherkr/claude-qwen-tts/tts-init)
Your own site
<a href="https://agentmods.dev/commands/harifatherkr/claude-qwen-tts/tts-init"><img src="https://agentmods.dev/badge/commands/harifatherkr/claude-qwen-tts/tts-init/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 tts-init

Your own site · 80×15
<a href="https://agentmods.dev/commands/harifatherkr/claude-qwen-tts/tts-init"><img src="https://agentmods.dev/badge/commands/harifatherkr/claude-qwen-tts/tts-init.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 720 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.
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 $0.00016 $0.00720
Opus 5 $0.00008 $0.00360
Sonnet 5 $0.00003 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured 12d ago against content hash d9f35b75de3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

tts-init 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 12d 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/claude-qwen-tts/commands/tts-init.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TTS-Init - Interactive Configuration

Set up TTS configuration through interactive questions.

Prerequisites

Check if /tts-setup has been run:

test -d ~/.config/claude-qwen-tts/venv && echo "Setup complete" || echo "Setup needed"

If setup needed, inform user: "Please run /tts-setup first."

Interactive Flow

Question 1: Reference Voice Selection

Ask the user using AskUserQuestion:

Question: "Select your reference voice for TTS:"

Options:

  • A) Use default sample (Korean male)
  • B) Use default sample (Korean female)
  • C) Register my own voice file

If Option A or B selected:

Set config based on selection:

  • A: ~/.config/claude-qwen-tts/samples/ko_male.wav
  • B: ~/.config/claude-qwen-tts/samples/ko_female.wav

Read the corresponding text file for reference text.

If Option C selected:

Ask: "Please provide the path to your voice file (5-10 seconds, WAV recommended):"

Then ask: "What is the exact transcript of the audio? (accuracy improves quality)"

Question 2: Default Output Directory

Ask the user:

Question: "Select default output directory:"

Options:

  • A) ./output (current project)
  • B) ~/Documents/tts-output (home directory)
  • C) Enter custom path

Save Configuration

Write to ~/.config/claude-qwen-tts/config.yaml:

reference:
  audio: PATH_TO_AUDIO
  text: "TRANSCRIPT_TEXT"

output:
  default_dir: OUTPUT_DIRECTORY
  sample_rate: 24000

environment:
  venv_path: ~/.config/claude-qwen-tts/venv
  device: auto
cat > ~/.config/claude-qwen-tts/config.yaml << 'EOF'
reference:
  audio: "AUDIO_PATH"
  text: "REFERENCE_TEXT"

output:
  default_dir: "OUTPUT_DIR"
  sample_rate: 24000

environment:
  venv_path: ~/.config/claude-qwen-tts/venv
  device: auto
EOF

Test Configuration

Run a quick test:

source ~/.config/claude-qwen-tts/venv/bin/activate && \
python ~/.config/claude-qwen-tts/scripts/tts_runner.py voice_clone \
  --text "설정 테스트입니다" \
  --output ~/.config/claude-qwen-tts/test_output.wav \
  --config ~/.config/claude-qwen-tts/config.yaml

Read the full file on GitHub · 123 lines

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. 12d ago First seen · 123 lines · 16 tokens per session scan A d9f35b75de3d

Subscribe to this mod's changes

tts-init is a command published in the GitHub repository HariFatherKR/claude-qwen-tts (16 stars, last pushed 7mo ago), licensed MIT. It adds 16 tokens to every session and 720 once invoked, about $0.0001 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 2026-08-30.