A post dated August 28, 2026, describes Phonon-1, a speech recognition model with 782 million parameters, a 415 MB download, and an Apache 2.0 license.
On August 28, 2026, a post announced Phonon-1, a speech recognition model with 782 million parameters, a 415 MB download, and an Apache 2.0 license. According to the post, the model transcribes one hour of audio in about two minutes on a MacBook Air; this is a reported claim, not an independently presented result.
The size, license, and reported speed may interest organizations evaluating self-hosted speech recognition models. Consult the original announcement for its details, and verify the license and performance on hardware and audio relevant to your use case. If you use AI to study or apply the material, do not submit sensitive recordings or documents without authorization, and follow your organization's data protection policies.