v0.55.1 v1.7.3

Name: Step-Audio
Author: stepfun-ai

stepfun-ai/Step-AudioOct 2, 2026 → Oct 2, 20260 days between releases

Generating AI comparison

Analyzing what changed between v0.55.1 and v1.7.3. This page updates automatically — usually within a minute.

The Two Releases

v0.55.1

Oct 2, 2026· 20 days ago

An update to the Siphon-AI daemon improving speech synthesis performance by switching the default TTS provider to Deepgram Aura and fixing a bug where bot audio was dropped after pause resolution.

Full release notes

v1.7.3

Oct 2, 2026· 20 days ago

A major feature release focusing on performance optimizations for object detection on Macs, new embedding capabilities for classifiers, and upgraded AI models, alongside various bug fixes and maintenance updates.

Full release notes