Inkling Open-Weight Model Supports Audio Transcription

ziqiao_ma · x · 2026-07-19

According to a summary by Artificial Analysis, Thinking Machines has released a new open-weight model named Inkling. It features 975B total parameters and 41B active parameters, supporting text, image, and audio inputs for speech transcription.

Tested on the AA-WER speech recognition leaderboard with a 256K context version, it achieved a 3.5% word error rate, ranking second among open-weight models, just behind Mistral's Voxtral Small (2.8%). The post also mentions that Inkling's weights are openly available on Hugging Face under the Apache 2.0 license, making it currently the largest open-weight model supporting transcription on that leaderboard.

Original post →

More from Models

Models channel →