helix-db Releases
177 releases of HelixDB/helix-db
- v0.90.1
A bug fix release that introduces support for React 19 and updates major package versions.
Feb 9, 2025
- v2.0.8
The first stable release of the MPFB (Make Human Facial Blendshapes) add-on for Blender.
Jan 28, 2025
- v0.89.4
A release focused on documentation corrections and improving terminal user experience during builds.
Nov 8, 2024
- v0.89.3
Bug fixes addressing command blocking issues and configuration handling.
Oct 8, 2024
- v3.1.2GUI for precise control
A new GUI is introduced to allow users to precisely control pitch, duration, and voice identity for synthesized audio across over 7000 languages.
Oct 7, 2024
- v0.908Windows-v0.908
A Windows-focused release that fixes interface display issues and provides distribution assets.
Aug 1, 2024
- v3.1Improved TTS in 7000 Languages
This release improves the universal TTS model by introducing stochastic prosody prediction, expanding language support, and overhauling language similarity visualization.
Jul 25, 2024
- v0.15.0Sherlock v0.15.0
A major overhaul adopting Poetry and official packaging across multiple platforms.
Jul 8, 2024
- v1.2.0Open-Sora v1.2.0 Released Today!
A major update to Open-Sora introducing video compression networks and rectified-flow training to enhance video generation quality and efficiency.
Jun 18, 2024
- v3.0TTS in 7000 Languages
This release introduces a massively multilingual Text-to-Speech model capable of speaking over 7000 languages, featuring improved quality, audio watermarking, and significant simplifications.
Jun 10, 2024
- 2.pPrompting Controlled Emotional TTS
This release enables emotional Text-to-Speech by allowing models to be conditioned on emotional prompts during training and transferring that emotion to synthesis during inference.
Jun 10, 2024
- v1.1.0Open-Sora V1.1.0 Release
Enhanced video generation capabilities including support for longer videos, higher resolutions, and image-to-video editing, plus a new automated data pipeline.
May 7, 2024
- v1.0.0Open-Sora V1.0.0 Release
The initial major release of Open-Sora, providing the complete open-source framework, optimized training pipelines, and initial model weights.
Mar 17, 2024
- v0.907clone-voice-v0.907
A maintenance release for the Clone-Voice application that addresses several bugs and updates documentation regarding the Coqui.ai model license.
Feb 28, 2024
- v0.901clone-voice-v0.901
A minor update focusing on updating the certificate and license documentation for the Coqui.ai models used in the software.
Jan 21, 2024
- v0.0.1模型下载
The initial release providing the core model files and data required for text-to-speech and speech-to-speech functionality in Clone-Voice.
Nov 19, 2023
- v3.1fixv3.1
Minimal release notes: "1.优化了内网穿透功能,bridge,client和server只需要启动一个即可。 server端启动的时候可以指定client端要暴露的一个或者多个端口。 2.修复了重复解析命令行参数的问题。 3.手册增加了微信接"
Oct 10, 2017