ops-voice

Automate phone calls, text-to-speech, and transcription via CLI.

22|6|Updated Apr 11, 2026
One-click install
npx skills add https://github.com/Lifecycle-Innovations-Limited/claude-ops --skill ops-voice
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ops-voice
Source: https://github.com/Lifecycle-Innovations-Limited/claude-ops/tree/main/claude-ops/skills/ops-voice
Command: npx skills add https://github.com/Lifecycle-Innovations-Limited/claude-ops --skill ops-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automates voice-based operations by enabling programmatic phone calls, speech synthesis, and audio transcription via a CLI, reducing manual handling and improving accessibility and automation.

Core Features & Use Cases

  • Automatic voice calls to phone numbers using Bland AI for task-based conversations.
  • Text-to-speech synthesis via ElevenLabs to generate natural-sounding audio from text.
  • Audio transcription using Groq Whisper to convert recordings into text for logging, analysis, or indexing.
  • Use cases include customer outreach, real-time alerts, media monitoring, and accessible content generation.

Quick Start

Run /ops:setup to configure API keys, then use /ops:voice call <phone> <prompt>, /ops:voice tts <text>, or /ops:voice transcribe <file> to perform tasks.

Frequently Asked Questions about ops-voice

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

FAQPage Schema
How do I automate voice calls and audio transcription from the command line?

You can automate voice calls and audio transcription from the command line by running CLI commands that use curl-based HTTP requests to trigger Bland AI calls and Groq Whisper transcription.

Do I need API keys to use text-to-speech synthesis and voice call automation?

Yes, you need API keys to use text-to-speech synthesis and voice call automation. You must configure keys for Bland AI, ElevenLabs, and Groq during setup before executing any tasks.

What's the best way to convert audio recordings into text for logging and analysis?

The best way to convert audio recordings into text for logging and analysis is using the transcription command, which sends audio files to Groq Whisper via curl for accurate speech-to-text conversion.

Can I generate natural-sounding speech from text via a CLI tool?

Yes, you can generate natural-sounding speech from text via a CLI tool by running the text-to-speech command, which sends your input text to ElevenLabs for audio synthesis.

Does this voice automation approach work for customer outreach and accessibility transcription?

Yes, this voice automation approach works for customer outreach and accessibility transcription by automating task-based phone calls and converting audio content into accessible text formats.

Why are my automated voice calls not working after setup?

Your automated voice calls might not be working due to missing or incorrect API keys for Bland AI, which are required to authenticate the curl-based HTTP requests for phone call automation.