metabot: Skill for Claude Code

.claude/skills/doubao-tts/SKILL.md

doubao-tts is a skill for Claude Code from xvirobotics/metabot. It costs 48 tokens per session (1,374 once invoked), scanned A, original, MIT.

A text-to-speech tool that turns written text into speech audio using Doubao, a Volcengine voice-synthesis service.

In plain words
What is it for?
Use it to create voiceovers, narrated content, podcasts, or other speech files, while selecting a voice and adjusting speed, volume, or pitch.
Why use it?
It removes the need to record narration manually and supports both short spoken text and longer audio generation.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is xvirobotics/metabot's own configuration. It tells Claude Code how to work on metabot itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything metabot configures →

Reuse

Borrowing it

Nothing to install: this file belongs to xvirobotics/metabot. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/xvirobotics/metabot/main/.claude/skills/doubao-tts/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/xvirobotics/metabot

Made for: Claude Code.

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 doubao-tts

README.md
[![agentmods](https://agentmods.dev/badge/skills/xvirobotics/metabot/doubao-tts/github.svg)](https://agentmods.dev/skills/xvirobotics/metabot/doubao-tts)
Your own site
<a href="https://agentmods.dev/skills/xvirobotics/metabot/doubao-tts"><img src="https://agentmods.dev/badge/skills/xvirobotics/metabot/doubao-tts/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 doubao-tts

Your own site · 80×15
<a href="https://agentmods.dev/skills/xvirobotics/metabot/doubao-tts"><img src="https://agentmods.dev/badge/skills/xvirobotics/metabot/doubao-tts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,374 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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: 2 findings, 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 Supply Chain · line 98
    Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
    Fix: Avoid downloading and executing remote scripts. Use trusted packages from PyPI/npm. If remote fetch is required, verify checksums and use HTTPS.
  • medium Data Exfiltration · line 98
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 $0.00048 $0.01374
Opus 5 $0.00024 $0.00687
Sonnet 5 $0.00010 $0.00275
Haiku 4.5 $0.00005 $0.00137

Measured 13d ago against content hash 41d1575c8eb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

doubao-tts scanned grade A with 1 finding 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 13d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

## Raw curl (if CLI not available)
.claude/skills/doubao-tts/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Doubao TTS — 豆包语音合成

Generate high-quality speech audio from text using Volcengine's Doubao TTS API. Supports short-form (real-time) and long-form (async, up to 100K characters) synthesis.

When to Use

  • User asks to generate audio, podcasts, voiceovers, or narration
  • User wants text-to-speech for any content
  • User asks to "read this aloud" or "make an audio version"

Quick Usage

Use the doubao-tts CLI tool (installed at bin/doubao-tts):

# Short text (real-time, < 300 chars)
bin/doubao-tts "你好世界" -o output.mp3

# Long text from file (async mode, up to 100K chars)
bin/doubao-tts -f article.txt -o podcast.mp3

# Pipe content
echo "Hello world" | bin/doubao-tts -o hello.mp3

# Choose voice
bin/doubao-tts "你好" -v zh_male_aojiaobazong_moon_bigtts -o output.mp3

# Adjust speed/volume/pitch
bin/doubao-tts "你好" --speed 1.2 --volume 1.5 -o output.mp3

Available Voices (已验证可用)

Chinese Female

Voice ID Description
zh_female_sajiaonvyou_moon_bigtts 撒娇女友 (default)
zh_female_gaolengyujie_moon_bigtts 高冷御姐
zh_female_tianmeixiaoyuan_moon_bigtts 甜美校园
zh_female_yuanqinvyou_moon_bigtts 元气女友
zh_female_wanwanxiaohe_moon_bigtts 弯弯小何
zh_female_linjianvhai_moon_bigtts 邻家女孩

Chinese Male

Voice ID Description
zh_male_aojiaobazong_moon_bigtts 傲娇霸总
zh_male_jingqiangkanye_moon_bigtts 京腔侃爷
zh_male_wennuanahu_moon_bigtts 温暖阿虎
zh_male_yangguangqingnian_moon_bigtts 阳光青年

Note: 其他音色 (BV系列, mars后缀) 需要不同的 resource ID。如需更多音色,请在火山引擎控制台开通对应资源。

API Details

Environment Variables (already configured in MetaBot .env)

VOLCENGINE_TTS_APPID=<app_id>
VOLCENGINE_TTS_ACCESS_KEY=<access_key>
VOLCENGINE_TTS_RESOURCE_ID=volc.service_type.10029  (optional)

Short-form API (real-time, < 300 chars)

  • Endpoint: https://openspeech.bytedance.com/api/v3/tts/unidirectional
  • Response: chunked JSON with base64 audio in data field
  • Latency: < 1 second

Read the full file on GitHub · 127 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. 13d ago First seen · 127 lines · 48 tokens per session scan A 41d1575c8eb4

Subscribe to this mod's changes

doubao-tts is a skill published in the GitHub repository xvirobotics/metabot (977 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 1,374 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.