Whisper Large v3 Turbo

An automatic speech recognition (ASR) model that can transcribe audio at an impressive 216x speed, making it highly efficient for fast and accurate speech-to-text conversion.

Supports a 448 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

Capable of generating structured output formats.

For ASR models, Groq charges a minimum of 10 seconds per request, and the maximum file size is 25 MB.