Groq - Whisper Turbo Large V3 vv3 Turbo

A pruned and fine-tuned version of Whisper Large v3, designed for faster and less expensive multilingual speech recognition while maintaining comparable accuracy.

Model ID

groq.whisper-large-v3-turbo

Use this ID when making API calls to reference this model

Provider

groq

Model Type

general

Accuracy Tier

enhanced

Release Date

August 1, 2024

Supported Languages

afarhyazbebsbgcazhhrcsdanlenetfifrgldeelhehihuisiditjaknkkkolvltmkmsmrminenofaplptrorusrskslesswsvtltathtrukurvicy
Automatic Language Detection: Yes
Performance & Cost

Cost

$0.04000/hour

$0.00001/second

Processing Speed

247x realtime

Maximum Duration

13m

Maximum File Size

25.00 MB

Features

Supported capabilities and functionalities

Core Features

Punctuation
Diarization
Streaming
Speaker Labels
Word Timestamps
Confidence Scores
Custom Vocabulary
Profanity Filtering
Noise Reduction
Voice Activity Detection

Subtitle Formats

SRT Support
VTT Support
Technical Specifications

Input/output formats and technical details

Subtitle Format Support

No subtitle formats supported

Supported Audio Encodings

FLACMP3MP4MPEGMPGAM4AOggWAVWebMOpus

Supported Sample Rates

16000 Hz