What tools are required for audio processing?

The skill installs fluent-ffmpeg and node-record-lpcm16 to handle audio format conversion and microphone capture during the setup process.

Which languages are supported by the Speak integration?

It supports over 14 languages, including Korean, Spanish, Japanese, French, German, Portuguese, Mandarin, and English.

What do I need before using this skill?

You need a Speak developer account, an OpenAI API key, and Node.js or Python installed in your environment.

Does this skill support Python?

Yes, while the primary examples are TypeScript-focused, the skill supports Python setup via pip and environment configuration.

How does Speak interact with OpenAI?

Speak leverages OpenAI's GPT-4o and Realtime API to provide low-latency speech processing and intelligent tutoring responses.

Speak API Installation & Auth

Name: Speak API Installation & Auth
Author: jeremylongshore

byjeremylongshore

•

1,844

•

Learning & Documentation

Configures Speak language learning API integration and authenticates OpenAI Realtime API for AI-powered tutoring.

This skill automates the setup of the Speak language learning platform within your development environment. It handles the installation of the Speak SDK and essential audio processing dependencies like OpenAI and fluent-ffmpeg, configures necessary environment variables for authentication, and initializes a ready-to-use client. It is ideal for developers building AI-driven language tutors or speech-to-speech applications that require real-time pronunciation feedback across multiple languages including Korean, Spanish, and Japanese.

Key Features

011,844 GitHub stars

02Ready-to-use TypeScript and Python initialization patterns

03Environment variable configuration for Speak and OpenAI credentials

04Multi-language support verification for 14+ languages

05Automated installation of Speak SDK and audio dependencies

06Seamless integration with OpenAI Realtime API for speech processing

Use Cases

01Adding real-time pronunciation feedback to an existing educational platform

02Initializing a new AI-powered language learning application

03Setting up a speech-to-speech tutoring pipeline using Whisper and Speak

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jeremylongshore/claude-code-plugins-plus-skills speak-install-auth

For use in Claude.ai and ChatGPT

Key Features

011,844 GitHub stars

02Ready-to-use TypeScript and Python initialization patterns

03Environment variable configuration for Speak and OpenAI credentials

04Multi-language support verification for 14+ languages

05Automated installation of Speak SDK and audio dependencies

06Seamless integration with OpenAI Realtime API for speech processing

Use Cases

01Adding real-time pronunciation feedback to an existing educational platform

02Initializing a new AI-powered language learning application

03Setting up a speech-to-speech tutoring pipeline using Whisper and Speak

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jeremylongshore/claude-code-plugins-plus-skills speak-install-auth

For use in Claude.ai and ChatGPT