skills.rest
antonyfmunoz
antonyfmunozCOMMUNITY
Explore all skills by this author →
GitHub

groq

Execute OpenAI-compatible chat completions and Whisper speech-to-text transcription via Groq APIs.

1|Updated Mar 11, 2026
Search Tags:#groq#openai-compatible#llm inference#streaming sse#json mode#whisper stt#discord voice
One-click install
npx skills add https://github.com/antonyfmunoz/OS --skill groq-antonyfmunoz
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: groq
Source: https://github.com/antonyfmunoz/OS/tree/main/skills/tools/groq
Command: npx skills add https://github.com/antonyfmunoz/OS --skill groq-antonyfmunoz

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Groq enables ultra-fast OpenAI-compatible chat completions and low-latency Whisper speech-to-text so you can reduce response time in conversational and voice workflows.

Core Features & Use Cases

  • Fast Inference (OpenAI-compatible chat): Send prompts to Groq’s /chat/completions endpoint for rapid text generation and tool/function calling, optimized for EOS routing and real-time UX.
  • Voice Transcription (Whisper STT): Transcribe Discord voice recordings via Groq’s native /audio/transcriptions (whisper-large-v3 or whisper-large-v3-turbo) for turning speech into actionable text.
  • Reliable Streaming & Structured Output: Use SSE streaming for token-by-token replies and JSON mode for structured extraction and function calling.

Quick Start

Set your Groq API key in the environment variable GROQ_API_KEY, then ask the AI to “Transcribe the attached audio using whisper-large-v3-turbo with language en, and return the transcript.”

Frequently Asked Questions about groq

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

FAQPage Schema
How do I get ultra-fast LLM inference for OpenAI-compatible chat completions?▼

Ultra-fast LLM inference is achieved by sending prompts to Groq's /chat/completions endpoint using the OpenAI SDK, requiring the GROQ_API_KEY environment variable for authentication and routing.

Can I use Groq Whisper speech-to-text transcription for Discord voice recordings?▼

Yes, Groq Whisper speech-to-text transcribes Discord voice recordings via the native Groq SDK /audio/transcriptions endpoint, using whisper-large-v3 or whisper-large-v3-turbo models with proper audio chunking.

How do I stream token-by-token replies and get structured JSON output from an LLM?▼

Streaming token-by-token replies use SSE streaming, while structured extraction and function calling utilize JSON mode, both supported via the OpenAI-compatible chat completions endpoint.

Do I need the native Groq SDK or the OpenAI SDK to transcribe large audio files?▼

Audio transcription requires the native Groq SDK for the /audio/transcriptions endpoint, whereas chat completions use the OpenAI SDK configured with the Groq API base URL.

What is the best way to implement fast-path and fallback routing for real-time conversational LLMs?▼

EOS model routing applies fast-path and fallback logic to OpenAI-compatible chat completions, optimizing real-time conversational UX by leveraging Groq's low-latency inference.

Related Skills

Explore More Software Engineering Skills→
badlogicbadlogic
2.3k

transcribe

Transcribe audio files to plain text via the Groq Whisper API.

Community
Advanced
reedmayhew18reedmayhew18
23

oc-voice

Transcribe voice chat messages with Whisper and route text downstream.

Community
Intermediate
davidrrowleydavidrrowley

azure-ai-voicelive-dotnet

Enable bidirectional AI voice sessions in .NET using WebSockets and Azure authentication.

Community
Intermediate
framerslabframerslab

whisper-transcribe

Transcribe audio and video files to text using OpenAI Whisper.

Official
Intermediate