dia2 Releases

This release introduces VoxCPM 1.5, focusing on enhancements to the voice model and related documentation updates.

Dec 5, 2025

Dec 3, 2025

Hanko 2.3 updates OAuth/OIDC integration by allowing connection management and removing email requirements for 3rd party identities.

Dec 3, 2025

A patch release focusing on bug fixes for menu race conditions, input scrolling, and editor positioning, plus a security upgrade for tracing-subscriber.

Nov 27, 2025

A minor update adding UI refinements like dropdown carets, line chart styling, and sidebar improvements.

Nov 20, 2025

This release focuses on improving API consistency and usability through a series of breaking changes, including renaming components like Modal to Dialog and Drawer to Sheet. It also introduces new components like Collapsible, enhances Input and Slider interactions, and adds a WebView Inspector feature.

Nov 17, 2025

Nov 16, 2025

Oct 31, 2025

This release introduces a centralized analytics dashboard, real-time webhooks for workflow integration, and significant enhancements to dataroom file permissions and document previews.

Aug 20, 2025

This release focuses on optimizing the translation service, fixing language detection bugs, and adding React support and advanced visual adjustments.

Aug 16, 2025

This release deepens integration with GiteeAI, adds lifecycle monitoring for rendering, and optimizes text processing, character splitting, and browser compatibility.

Jul 4, 2025

This release enhances communication and organization within datarooms by adding Q&A conversations, file requests, presets, and tags, alongside improved document management UX.

Apr 30, 2025

This release introduces team collaboration tools like user invitations and global branding, alongside productivity features such as automatic index file generation and quality-of-life updates for video files and dashboards.

Mar 12, 2025

This release adds a graphical user interface (GUI) that enables precise control over speech synthesis, allowing users to adjust pitch, duration, and voice settings across 7000+ languages.

Oct 7, 2024

This minor release significantly improves audio quality by switching the vocoder training to an end-to-end approach using synthetic spectrograms, resulting in better sound without a loss in inference speed.

Sep 22, 2024

This release refines the universal TTS model by introducing stochastic prosody prediction and expanding language support capabilities. It serves as a refinement of the v3.0 release to address initial limitations and improve speech generation quality.

Jul 25, 2024

This release marks a major milestone by enabling Text-to-Speech for over 7000 languages through an extrapolation technique. It includes quality enhancements and a new watermarking feature to prevent misuse.

Jun 10, 2024

This release introduces prompt-based emotional conditioning for TTS models, allowing users to synthesize speech with specific emotions during both training and inference.

Jun 10, 2024