groq-core-workflow-b

name	groq-core-workflow-b
description	Use when you need Groq's non-chat endpoints — transcribing or translating audio with Whisper, understanding images with Llama 4 vision, generating speech (TTS), or benchmarking models for speed vs quality. Trigger with phrases like "groq whisper", "groq transcription", "groq audio", "groq vision", "groq TTS", "groq speech".
allowed-tools	Read, Bash(npm:*)
version	1.11.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","groq","workflow","audio","vision"]
compatibility	Designed for Claude Code

Groq Core Workflow B: Audio, Vision & Speech

Overview

Beyond chat completions, Groq offers ultra-fast Whisper transcription (216x real-time), Llama 4 vision, and text-to-speech — all on the same groq-sdk client. This skill covers transcription/translation, vision, TTS, and model benchmarking, with full runnable code in references/implementation.md and worked scripts in references/examples.md.

Prerequisites

• groq-sdk installed, GROQ_API_KEY set (the SDK reads it from the environment automatically)
• For audio: audio files in a supported format
• For vision: image URLs or base64-encoded images

Audio Models

Model ID	Languages	Speed	Best For
whisper-large-v3	100+	164x real-time	Best accuracy, multilingual
whisper-large-v3-turbo	100+	216x real-time	Best speed/accuracy balance

Supported audio formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, webm

Instructions

Each workflow is a single SDK call on the shared groq client. Pick the endpoint for your task, then follow the full walkthrough in references/implementation.md for the complete, copy-pasteable version of each.

1. Transcription — groq.audio.transcriptions.create({ file, model: "whisper-large-v3-turbo", response_format }). Use response_format: "verbose_json" with timestamp_granularities: ["segment"] to get per-segment start/end times.
2. Translation — groq.audio.translations.create({ file, model: "whisper-large-v3" }) transcribes any-language audio directly to English text.
3. Vision — a normal groq.chat.completions.create call where content is an array mixing and parts. Accepts up to 5 images (URL or base64) with .