voice-reply

Name: voice-reply
Availability: InStock
Author: leto-labs

Convert text into spoken audio via OpenAI's TTS API.

Updated Jan 15, 2026

Search Tags:#voice #text-to-speech #audio #openai #tts #telegram #speech-synthesis

Ready to run

npx skills add https://github.com/leto-labs/jarvis-template --skill voice-reply

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: voice-reply
Source: https://github.com/leto-labs/jarvis-template/tree/main/Database/Skills/voice-reply
Command: npx skills add https://github.com/leto-labs/jarvis-template --skill voice-reply

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Quickly transform written content into natural-sounding spoken audio, enabling audio-based communication without manual TTS setup.

Core Features & Use Cases

Convert text to speech using OpenAI's Text-to-Speech API for instant audio replies
Produce audio notes in opus format suitable for Telegram voice messages
Offer multiple voices and adjustable speed, with simple one-shot usage

Quick Start

Provide the text to convert to speech and the skill will generate an audio voice note using the selected voice and speed.

Frequently Asked Questions about voice-reply

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

FAQPage Schema

How do I convert text to speech for Telegram voice messages?▼

To convert text to speech for Telegram voice messages, this skill uses OpenAI's TTS API to generate audio in opus format. It processes the provided text, removes emojis, and outputs a natural-sounding voice note ready for delivery.

Can I adjust the speed or choose different voices for OpenAI TTS audio replies?▼

Yes, you can adjust speed settings and choose from multiple voices when generating OpenAI TTS audio replies. The skill supports configurable voice selection and speed adjustments to customize the spoken output.

Does the voice-reply skill work without any external dependencies?▼

The voice-reply skill operates without internal component dependencies, but it requires an OpenAI API key to function. It uses curl to call the OpenAI TTS API directly for speech synthesis and audio delivery.

What is the best way to generate natural phrasing from text using text-to-speech?▼

The best way to generate natural phrasing from text using text-to-speech is to pass the content through the skill's processing logic. It strips emojis and handles natural phrasing adjustments before sending the text to the speech synthesis API.

Are there limitations when using OpenAI TTS for speech synthesis in Telegram?▼

Limitations when using OpenAI TTS for speech synthesis in Telegram include dependency on the OpenAI API for processing and the need to format output specifically as opus audio. The skill handles this format conversion automatically for proper voice note delivery.