Volcengine Ai Audio Tts

Text-to-speech generation on Volcengine audio services. Use when users need narration, multi-language speech output, voice selection, or TTS troubleshooting.

Security Scan

The skill's stated purpose (Volcengine TTS) is plausible, but the runtime instructions are high-level and the package fails to declare the credentials/endpoints a real Volcengine integration would need, leaving its actual behavior underspecified.

Purpose & Capability

Name and description claim Volcengine text-to-speech, which reasonably implies calls to Volcengine APIs. However the skill declares no required environment variables, no primary credential, and provides no endpoint or auth guidance — a real Volcengine integration normally requires API keys/secret and explicit endpoint/parameter mappings. The lack of declared credentials or source/homepage is a mismatch.

Instruction Scope

SKILL.md gives a short checklist (confirm text/voice, set format, execute request, return URL/path) but is vague about how to 'execute TTS request' (which endpoint, what auth, where to store resulting audio). It does not instruct reading unrelated files or secrets, but grants broad discretion to perform network calls and polling without constraints or safety rules.

Install Mechanism

Instruction-only skill with no install spec and no code files — lowest install risk. There are no downloads or new binaries introduced.

Credentials

No environment variables or credentials are declared, yet the intended functionality requires service credentials (e.g., Volcengine API key/secret). The omission means callers/agents might rely on ambient credentials or be prompted to add secrets dynamically, which is a proportionality and transparency issue.

Persistence & Privilege

always:false and no config writes or persistence instructions. The skill does not request elevated or permanent presence; autonomous invocation is allowed (platform default) but is not combined with other high-privilege requests here.

What to consider before installing

This skill is a high-level checklist for using Volcengine TTS but leaves out crucial details. Before installing or using it, ask the publisher: (1) exactly which Volcengine endpoints and API parameters it will call; (2) what environment variables (names) it needs (e.g., VOLCENGINE_API_KEY) and why; (3) where audio files will be uploaded/stored and how long they persist; and (4) whether any user text or audio is logged or sent to other endpoints. If you supply credentials, prefer creating a minimal-scope API key and test in an isolated account. Because the skill is instruction-only (no code to inspect), the platform scanner had nothing to analyze — exercise extra caution and require the author to declare auth/environment requirements and privacy/retention policies before trusting it with sensitive data.

Synthesize speech from text with voice, language, and format controls.

Execution Checklist

1. Confirm input text, language, and target voice.
2. Set output format and sample rate.
3. Execute TTS request and poll if async.
4. Return audio URL/path and reproducible parameters.

Output Rules

• Prefer stable audio formats (mp3 or wav).
• Keep text chunks short for long passages.
• Surface duration and file size when possible.

References

• references/sources.md