voice-config

Configure voice transcription and TTS providers for an AI gateway.

Updated Feb 16, 2026

Search Tags:#configuration #voice #transcription #setup #audio #tts

Ready to run

npx skills add https://github.com/michaeljabbour/amplifier-bundle-letsgo --skill voice-config

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: voice-config
Source: https://github.com/michaeljabbour/amplifier-bundle-letsgo/tree/main/skills/voice-config
Command: npx skills add https://github.com/michaeljabbour/amplifier-bundle-letsgo --skill voice-config

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill simplifies the setup and configuration of voice transcription and text-to-speech (TTS) providers for your AI assistant, ensuring seamless audio input and output.

Core Features & Use Cases

Flexible Provider Selection: Choose between OpenAI Whisper API or local Whisper for transcription, and edge-tts, ElevenLabs, or OpenAI TTS for speech synthesis.
Secure API Key Management: Integrates with a secrets manager for secure storage of API keys.
Use Case: You want to enable your AI assistant to understand spoken commands and respond with synthesized speech. This Skill guides you through selecting and configuring Whisper for transcription and ElevenLabs for high-quality TTS output.

Quick Start

Configure the voice settings in your gateway config file to enable transcription using the Whisper API.

Frequently Asked Questions about voice-config

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

FAQPage Schema

How do I configure voice transcription and TTS for an AI gateway?▼

To configure voice transcription and TTS for an AI gateway, you need to define your preferred providers and manage secure API keys within your gateway configuration files. This setup enables seamless audio input and synthesized speech output for your assistant.

Can I use local Whisper for voice transcription instead of the OpenAI API?▼

Yes, you can use local Whisper for voice transcription instead of the OpenAI Whisper API. This flexible provider selection allows you to choose between local processing and cloud API integration based on your specific hardware and latency requirements.

What text-to-speech providers are supported for AI assistant voice configuration?▼

Supported text-to-speech providers for AI assistant voice configuration include edge-tts, ElevenLabs, and OpenAI TTS. You can select any of these options to enable synthesized speech output directly through your gateway settings.

How do I securely manage API keys when setting up text-to-speech providers?▼

To securely manage API keys when setting up text-to-speech providers, you should integrate with a secrets manager. This ensures secure storage and prevents exposing sensitive provider credentials for services like ElevenLabs or OpenAI TTS.

Does edge-tts work with local Whisper for a completely offline voice setup?▼

Configuring edge-tts with local Whisper allows you to build a localized voice pipeline. While local Whisper handles audio transcription offline, edge-tts manages the text-to-speech synthesis, both integrated directly via your gateway configuration.