tts-voice-policy

Detect text language and enforce approved TTS voice selection for French and English.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/gevrey/openclaw_backup --skill tts-voice-policy
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tts-voice-policy
Source: https://github.com/gevrey/openclaw_backup/tree/main/skills/tts-voice-policy
Command: npx skills add https://github.com/gevrey/openclaw_backup --skill tts-voice-policy

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enforce consistent voice selection for TTS requests to prevent mismatches and accidental use of incorrect voices.

Core Features & Use Cases

  • Detects the source text language and routes to an approved voice.
  • If no voice is provided, prompts the user to choose between language-specific options.
  • Enforces that audio generation occurs only after explicit voice confirmation, and includes the voice in the completion message.

Quick Start

Invoke the policy on a TTS request to enforce language-appropriate voice selection.

Frequently Asked Questions about tts-voice-policy

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I enforce approved TTS voice choices for audio generation?

To enforce approved TTS voice choices, you can apply a voice policy that detects the source text language and restricts generation to defined voice pairs. This prevents mismatches and accidental use of incorrect voices.

What's the best way to prevent TTS audio generation without explicit voice selection?

Preventing TTS audio generation without explicit voice selection requires implementing guardrails that prompt the user to choose a voice when none is specified and block generation until explicit voice confirmation is received.

How does language detection work for routing TTS to approved voices?

Language detection for routing TTS works by analyzing the input text and matching it to language-specific approved voice pairs. This ensures the generated audio uses a voice appropriate for the detected language.

Can I use this TTS voice policy for both French and English text?

Yes, this TTS voice policy applies to both French and English text. It detects the source language and prompts the user to select between the defined language-specific voice options for accurate audio generation.

Why does my TTS voice selection need guardrails and final output confirmation?

TTS voice selection needs guardrails to prevent inconsistent voice choices and mismatched audio. Confirming the voice used in the final output message enforces that generation occurred only after explicit voice selection.