Step-Audio Releases

This release focuses on bug fixes and dependency updates, specifically improving text normalization in the Coqui Engine and stream status reporting, while relaxing validation for the Orpheus Engine.

May 3, 2025

This update introduces configurable silence control within the stream, migrates KokoroEngine to KokoroVoice, and enhances OrpheusEngine with model selection and stop-on-demand improvements.

Apr 19, 2025

A comprehensive update adding group chat functionality, Silero-VAD voice detection, CosyVoice2 text-to-speech support, and a web-based frontend toolset, alongside significant improvements to configuration management and code refactoring.

Feb 19, 2025

This release marks a complete architectural overhaul featuring a new frontend and backend, introducing vision capabilities, desktop pet modes, support for multiple new LLM providers including DeepSeek R1, and a comprehensive documentation site.

Feb 4, 2025

A patch release correcting the default ASR provider, which had been mistakenly set to faster-whisper without notice, causing issues for users without CUDA cuDNN.

Dec 21, 2024

A comprehensive update introducing new integrations (MailerLite, JotForm, ClickUp), REST API enhancements, and the introduction of a monaco editor for code execution.

Nov 18, 2024

A minor patch release focusing on PWA removal, exposing installation status in the API, and fixing parameter computation logic to handle unparsed numbers.

Aug 2, 2024

An update introducing a new flow editor feature, user invitation functionality, and a suite of REST API endpoints for managing users, flows, and data, alongside various UI and security improvements.

Aug 2, 2024

This release introduces several new integrations including Disqus, Google Tasks, Vtiger CRM, YNAB, Airtable, and Appwrite, alongside various triggers and actions for these platforms. It also includes infrastructure improvements to Docker configurations and enhanced SAML support.

May 28, 2024