Groq provides extremely fast inference for both speech-to-text and LLM tasks. Their custom Language Processing Unit (LPU) hardware delivers industry-leading speed for Whisper transcription and Llama-based text processing. Use Groq for the fastest cloud transcription available, or as an LLM provider for custom prompts and post-processing.
Features
Fastest cloud transcription available
Multiple Whisper model variants
LLM processing with Llama and GPT-OSS models
Free tier with generous rate limits
OpenAI-compatible API
Transcription Models
Model
ID
Whisper Large V3
whisper-large-v3
Whisper Large V3 Turbo
whisper-large-v3-turbo
LLM Models
Model
ID
Llama 3.3 70B
llama-3.3-70b-versatile
Llama 3.1 8B
llama-3.1-8b-instant
GPT-OSS 120B
gpt-oss-120b
Configuration
API Key - Sign up at console.groq.com and generate a free API key.
Setup
Open TypeWhisper Settings > Plugins
Find the Groq plugin and click Configure
Enter your Groq API key
Select Groq as your transcription engine or LLM provider
