Stay up to date with the latest Whisper Large v3 updates, new features, and improvements. Here's what changed in 2026.
As of early 2026, Whisper Large v3 remains OpenAI's flagship open
weight ASR model with no new major version released since November
However, the ecosystem has evolved significantly: Whisper Large v3 Turbo (released late 2024) offers a distilled variant with ~4x faster inference at minimal accuracy loss, making it the preferred choice for latency
The Distil
Whisper project has matured with community
On the tooling side, Hugging Face's Transformers library has added Flash Attention 2 support and improved batched long
The model's cumulative downloads continue to grow steadily, cementing its position as the de facto open ASR baseline. OpenAI has not announced a Whisper Large v4, and the community's focus has shifted toward efficient serving (quantized and distilled variants) and fine
tuning for specialized domains rather than waiting for a new base model release.
Whisper Large v3 is actively developing new features. Check back regularly or follow their official channels for the latest updates.
Follow their release notes for instant updates
Test the latest updates in your workflow
Help shape future development with your input
Try out all the new features and improvements that make Whisper Large v3 even more powerful.
Changelog last updated March 2026