What audio format does the Speak SDK Patterns skill support?

The skill includes patterns to convert audio into WAV 16kHz mono PCM using ffmpeg, which is the specific format required for successful Speak API ingestion.

How does this skill handle API rate limiting?

It provides a robust 'Retry with Backoff' pattern that automatically parses 'retry-after' headers and manages 429 status codes to ensure high availability.

What are the requirements for using this skill?

You need valid Speak API credentials, the 'speak-install-auth' skill configured, and ffmpeg installed on your system for audio processing.

Does it support tracking user progress?

Yes, it includes a dedicated Progress Tracker pattern for monitoring session duration, average pronunciation scores, and unique vocabulary learned over time.

Speak SDK Patterns

Name: Speak SDK Patterns
Author: jeremylongshore

byjeremylongshore

•

1,844

•

API 开发

Implements production-grade patterns for the Speak language learning API, including session management and audio processing.

The Speak SDK Patterns skill provides developers with standardized implementation templates for the Speak language learning API. It offers robust solutions for managing multi-turn conversation sessions, handling audio preprocessing with ffmpeg to meet strict API requirements, and implementing resilient communication patterns like exponential backoff. This skill is essential for building production-ready language learning applications that require high-quality pronunciation assessment, vocabulary tracking, and stable integration with the Speak platform.

主要功能

01Conversation session management for multi-turn learning

02Automated audio preprocessing for WAV 16kHz mono requirements

03Integrated learning progress and vocabulary tracking

04Advanced pronunciation assessment and scoring patterns

051,844 GitHub stars

06Resilient API retry logic with smart backoff handling

使用场景

01Implementing scalable session management for high-traffic educational apps

02Building custom AI-driven language learning interfaces

03Standardizing audio processing workflows for Speak API compatibility

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jeremylongshore/claude-code-plugins-plus-skills speak-sdk-patterns

For use in Claude.ai and ChatGPT

主要功能

01Conversation session management for multi-turn learning

02Automated audio preprocessing for WAV 16kHz mono requirements

03Integrated learning progress and vocabulary tracking

04Advanced pronunciation assessment and scoring patterns

051,844 GitHub stars

06Resilient API retry logic with smart backoff handling

使用场景

01Implementing scalable session management for high-traffic educational apps

02Building custom AI-driven language learning interfaces

03Standardizing audio processing workflows for Speak API compatibility

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add jeremylongshore/claude-code-plugins-plus-skills speak-sdk-patterns

For use in Claude.ai and ChatGPT