OpenParable
Skip to content
← Back to skills

Speak Core Workflow B

Development
speak-core-workflow-b

Speak Core Workflow B is an Agent Skill for development published in the jeremylongshore/claude-code-plugins-plus-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Execute Speak secondary workflow: Pronunciation Training with phoneme-level analysis. Use when implementing pronunciation drills, speech scoring, or targeted pronunciation improvement features. Trigger with phrases like "speak pronunciation training", "speak speech scoring", "speak phoneme analysis".

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/jeremylongshore/claude-code-plugins-plus-skills/blob/HEAD/plugins/saas-packs/speak-pack/skills/speak-core-workflow-b/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/speak-core-workflow-b, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Speak Core Workflow B: Pronunciation Training

Overview

Secondary workflow for Speak: detailed pronunciation training with phoneme-level analysis and adaptive practice. Uses OpenAI's speech recognition with Speak's proprietary proficiency graph to identify and drill weak phonemes.

Prerequisites

  • Completed speak-core-workflow-a
  • Audio recording capability (WAV 16kHz mono)
  • ffmpeg installed for audio preprocessing

Instructions

Step 1: Pronunciation Assessment

import { SpeakClient } from '@speak/language-sdk';

const client = new SpeakClient({
  apiKey: process.env.SPEAK_API_KEY!,
  appId: process.env.SPEAK_APP_ID!,
  language: 'es',
});

// Assess pronunciation of a specific phrase
const result = await client.assessPronunciation({
  audioPath: './recordings/hola-como-estas.wav',
  targetText: 'Hola, como estas?',
  language: 'es',
  detailLevel: 'phoneme',
});

console.log(`Overall score: ${result.score}/100`);
for (const word of result.words) {
  const flag = word.score < 70 ? 'WEAK' : 'OK';
  console.log(`  [${flag}] "${word.text}": ${word.score}/100`);
  if (word.phonemes) {
    for (const p of word.phonemes.filter(p => p.score < 70)) {
      console.log(`    Phoneme "${p.symbol}": ${p.score} — ${p.suggestion}`);
    }
  }
}

Step 2: Adaptive Drill Loop

async function pronunciationDrill(
  client: SpeakClient,
  phrases: string[],
  language: string,
  targetScore: number = 80,
  maxAttempts: number = 3,
) {
  const weakPoints: Map<string, number[]> = new Map();
  const results: DrillResult[] = [];

  for (const phrase of phrases) {
    let bestScore = 0;
    let attempts = 0;

    while (bestScore < targetScore && attempts < maxAttempts) {
      const audioPath = await recordStudentAudio(phrase);
      const result = await client.assessPronunciation({
        audioPath, targetText: phrase, language, detailLevel: 'phoneme',
      });

      bestScore = Math.max(bestScore, result.score);
      attempts++;

      // Track weak phonemes
      for (const word of result.words) {
        for (const p of (word.phonemes || []).filter(p => p.score < 70)) {
          const scores = weakPoints.get(p.symbol) || [];
          scores.push(p.score);
          weakPoints.set(p.symbol, scores);
        }
      }

      if (result.score >= targetScore) {
        console.log(`"${phrase}": PASSED (${result.score}/100, ${attempts} attempts)`);
      } else if (attempts < maxAttempts) {
        console.log(`"${phrase}": ${result.score}/100 — try again`);
      }
    }

    results.push({ phrase, bestScore, attempts });
  }

  return { results, weakPoints };
}

Step 3: Weakness Report

function generateWeaknessReport(weakPoints: Map<string, number[]>) {
  const report = [...weakPoints.entries()]
    .map(([phoneme, scores]) => ({
      phoneme,
      avgScore: Math.round(scores.reduce((a, b) => a + b, 0) / scores.length),
      occurrences: scores.length,
    }))
    .sort((a, b) => a.avgScore - b.avgScore);

  console.log('\\n=== Pronunciation Weakness Report ===');
  for (const entry of report.slice(0, 10)) {
    const bar = '█'.repeat(Math.round(entry.avgScore / 10));
    console.log(`  ${entry.phoneme.padEnd(5)} ${bar} ${entry.avgScore}/100 (${entry.occurrences}x)`);
  }
  return report;
}

Step 4: Targeted Practice Generator

async function generateTargetedPractice(
  client: SpeakClient,
  weakPhonemes: string[],
  language: string,
) {
  // Request phrases that emphasize specific phonemes
  const practice = await client.getPracticePhrasesForPhonemes({
    phonemes: weakPhonemes,
    language,
    difficulty: 'progressive', // Start easy, increase complexity
    count: 10,
  });

  console.log('Targeted practice phrases:');
  for (const phrase of practice.phrases) {
    console.log(`  "${phrase.text}" — targets: ${phrase.targetPhonemes.join(', ')}`);
  }
  return practice;
}

Workflow Comparison

AspectWorkflow A (Conversation)Workflow B (Pronunciation)
FocusNatural dialoguePhoneme accuracy
FeedbackGrammar + vocabularyPhoneme scores + mouth position
Sessions5-15 min conversations2-5 min drills
ScoringOverall fluencyPer-phoneme breakdown
Use caseCommunication practiceAccent reduction

Output

  • Phoneme-level pronunciation scores
  • Adaptive drill loop with retry on weak phrases
  • Weakness report showing problematic phonemes
  • Targeted practice phrase generation
  • Progress tracking over multiple sessions

Error Handling

ErrorCauseSolution
Audio too shortRecording < 0.5sMinimum 0.5s audio required
Background noisePoor recording environmentPrompt for quieter location
Phoneme not detectedUnclear speechSlow down and articulate
Score always lowMicrophone qualityTest with known-good audio first

Resources

Next Steps

For common errors, see speak-common-errors.

Examples

Basic drill: Assess pronunciation of 5 common Spanish phrases, identify weak phonemes, and generate a targeted practice set.

Progress tracking: Run daily pronunciation drills, track phoneme scores over time, and visualize improvement trends.