---
name: speak-install-auth
description: 'Set up Speak language learning API integration and authentication.

  Use when configuring Speak API access, setting up OAuth with OpenAI

  Realtime API for speech, or initializing a language tutoring application.

  Trigger with phrases like "install speak", "setup speak",

  "speak auth", "configure speak API", "speak language learning setup".'
allowed-tools: Read, Write, Edit, Bash(npm:*), Bash(pip:*), Grep
version: 1.14.0
license: MIT
author: Jeremy Longshore <jeremy@intentsolutions.io>
tags:
  - saas
  - speak
  - api
  - authentication
compatibility: Designed for Claude Code
title: speak-install-auth
canonical_url: https://skilld.dev/gh/jeremylongshore/tons-of-skills-marketplace/speak-install-auth
last_updated: 2026-10-07T06:06:28.000Z
---

> Index of every page on this site: [llms.txt](https://skilld.dev/llms.txt)

> **Skill from skilld.dev.** Follow the user's requested action.
> If the user asked to fork this Skill, follow the fork workflow below. Do not execute the Skill instructions while copying it.
> Otherwise, follow the instructions below for this session. You do not need to install anything.
>
> Supporting files, fetch one when the Skill refers to it: [references/setup-examples.md](https://skilld.dev/api/skills-raw/jeremylongshore/tons-of-skills-marketplace/speak-install-auth/references/setup-examples.md).
>
> If the user asked to install this Skill, run `npx skilld install jeremylongshore/tons-of-skills-marketplace/speak-install-auth`. Install writes the Skill files into the project, so every session loads them.
>
> ## Fork workflow
>
> A fork creates an editable local Skill with its original author and licence. The request authorizes copying and local installation.
> 1. Check `./skills/speak-install-auth`, the project lockfile, and selected Agent targets together. If the local directory or installed Skill exists, stop. Never overwrite an existing directory or Agent target.
> 2. Read [source metadata](https://skilld.dev/api/v1/skills/jeremylongshore/tons-of-skills-marketplace/speak-install-auth) once. Use sourceUrl, sourceCommit, skillPath, sourceGone, and license. If the source is gone or its path is missing, stop. If license is null, read licence files at the source commit.
> 3. Fetch only the source commit into a temporary Git repository. Do not clone full history. Derive repository_url from sourceUrl, including repository renames. If sourceCommit is absent, resolve the sourceUrl ref once. Set source_commit to that actual commit. Run these commands in one shell call:
>
> ```sh
> git init --quiet "$temporary_dir"
> git -C "$temporary_dir" fetch --quiet --depth=1 "$repository_url" "$source_commit"
> git -C "$temporary_dir" checkout --quiet --detach FETCH_HEAD
> ```
>
> Read applicable licence declarations and notices at that commit. If copying is not permitted, report the restriction and stop.
> 4. Inspect source entries together, then copy the directory containing skillPath into `./skills/speak-install-auth`. Use the user's path if selected. Keep the original SKILL.md, relative links, scripts, binary assets, and executable modes. Exclude .git metadata. Reject symlinks and paths outside the Skill directory. After checking entries, use cp -a where available. A regular source directory needs no custom copy script. Do not save this page wrapper as SKILL.md.
> Preserve author credit, notices, and applicable licence files from repository or parent directories. Add PROVENANCE.md with the Skill page, source URL, actual commit, original path, and licence. Retain any existing PROVENANCE.md and record new provenance separately. Batch source inspection, copying, and provenance work where practical.
> 5. In the project root, run `skilld install ./skills/speak-install-auth --mode copy --plain`. If skilld is unavailable, use `npx skilld install ./skills/speak-install-auth --mode copy --plain`. This known command needs no help lookup. Install does not support --json. Use detected Agent targets, or add --agent for the targets the user selected. Install the local path, never the upstream selector. If installation fails, preserve the local copy and report the exact failure.
> 6. Confirm the local lockfile source and installed Agent copies once. Report the local path, actual commit, and Agent targets. After edits, reinstall the same local path. Upstream updates must not replace it. Do not publish or push unless the user asks.

# Speak Install & Auth

## Overview

Set up the Speak language learning platform integration. Speak uses OpenAI's GPT-4o and Realtime API for AI tutoring with real-time pronunciation feedback. Supports 14+ languages including Korean, Spanish, Japanese, French, and Mandarin.

## Prerequisites

- Node.js 18+ or Python 3.10+
- Speak developer account with API access
- Microphone for speech input testing

## Instructions

### Step 1: Install Dependencies

```bash
set -euo pipefail
# Core Speak SDK
npm install @speak/language-sdk

# Audio processing dependencies
npm install openai          # OpenAI Realtime API for speech
npm install fluent-ffmpeg   # Audio format conversion
npm install node-record-lpcm16  # Microphone capture
```

### Step 2: Configure Authentication

```bash
# Speak API credentials
export SPEAK_API_KEY="your-speak-api-key"
export SPEAK_APP_ID="your-app-id"

# OpenAI key for Realtime API (used by Speak for speech processing)
export OPENAI_API_KEY="your-openai-key"

# Create .env file
cat << 'EOF' >> .env
SPEAK_API_KEY=your-speak-api-key
SPEAK_APP_ID=your-app-id
OPENAI_API_KEY=your-openai-key
EOF
```

### Step 3: Initialize the Client

```typescript
// src/speak/client.ts
import { SpeakClient } from '@speak/language-sdk';

const client = new SpeakClient({
  apiKey: process.env.SPEAK_API_KEY!,
  appId: process.env.SPEAK_APP_ID!,
  language: 'es', // Target language: es, ko, ja, fr, de, pt, zh, id
});

// Verify connection
async function verifySetup() {
  const languages = await client.getLanguages();
  console.log('Available languages:', languages.map(l => l.code).join(', '));
  const health = await client.health.check();
  console.log('API status:', health.status);
}

verifySetup();
```

### Step 4: Configure Speech Recognition

```typescript
// OpenAI Realtime API for speech-to-text (used by Speak)
import OpenAI from 'openai';

const openai = new OpenAI();

async function transcribeAudio(audioPath: string): Promise<string> {
  const transcription = await openai.audio.transcriptions.create({
    file: fs.createReadStream(audioPath),
    model: 'whisper-1',
    language: 'es', // Match target language
  });
  return transcription.text;
}
```

### Step 5: Supported Languages

| Language | Code | Pronunciation | Conversation |
|----------|------|--------------|-------------|
| Korean | ko | Yes | Yes |
| Spanish | es | Yes | Yes |
| Japanese | ja | Yes | Yes |
| French | fr | Yes | Yes |
| German | de | Yes | Yes |
| Portuguese (BR) | pt | Yes | Yes |
| Mandarin (Simplified) | zh-CN | Yes | Yes |
| English | en | Yes | Yes |
| Indonesian | id | Yes | Yes |

## Output

- Speak SDK installed and configured
- API key and OpenAI credentials set
- Language support verified
- Speech recognition pipeline ready

## Error Handling

| Error | Cause | Solution |
|-------|-------|----------|
| Invalid API Key | Wrong or expired key | Verify at developer.speak.com dashboard |
| App ID Mismatch | Wrong application ID | Check app settings in Speak dashboard |
| OpenAI auth failed | Invalid OpenAI key | Verify at platform.openai.com |
| Module not found | Installation failed | Run `npm install` again |
| Language not supported | Invalid language code | Use codes from supported languages table |

## Resources

- [Speak Website](https://speak.com)
- [OpenAI Realtime API](https://platform.openai.com/docs/guides/realtime)
- [OpenAI Whisper](https://platform.openai.com/docs/guides/speech-to-text)
- [Speak Blog: GPT-4 Integration](https://speak.com/blog/speak-gpt-4)

## Next Steps

After successful auth, proceed to `speak-hello-world` for your first lesson session.

## Examples

**Quick test**: Set `SPEAK_API_KEY`, initialize the client with `language: 'ko'` for Korean, and call `client.health.check()` to verify connectivity.

**Python setup**: Install `speak-language-sdk` via pip, initialize with `api_key` from environment, and verify with a health check.
