VideoLingo Releases
52 releases of Huanshere/VideoLingo
- 0.78.1
Bug fix release for `KeyPress` actions where AI-emitted Android key names (like DEL) failed due to Maestro's limited key lookup. The update improves key name resolution and provides actionable error feedback.
Aug 27, 2026
- v0.46.0
Improves the `find` command behavior and fixes various stability issues across Windows, Git, and stream handling.
Aug 26, 2026
- 0.78.0
Adds Anthropic Claude as a first-class AI provider and allows `imageAssertions` on reusable calls for call-site verification.
Aug 19, 2026
- 0.77.0
Introduces iOS real device support, a new `instruction` command for manual reproduction, and upgrades the underlying Maestro engine.
Jul 23, 2026
- 0.76.1
Fixes the rendering of the scenario graph to accurately reflect execution order by drawing dependency edges from the last reusable call node.
Jul 13, 2026
- 0.76.0
Introduces a scenario graph view for visualization and built-in guides for AI coding agents.
Jul 13, 2026
- v3.0.1
Adds RTX 50 series GPU support and upgrades core dependencies including PyTorch and whisperX.
Feb 28, 2026
- v3.0.0
Major release focusing on code refactoring for improved maintainability, significantly enhanced transcription quality through dual ASR approach, and added cloud API support for users without local GPUs.
May 5, 2025
- v2.2.1
Minor update adding SiliconFlow CosyVoice2.0 API integration for few-shot voice cloning capabilities.
Feb 16, 2025
- v2.2.0
Added cloud API support enabling VideoLingo to run without local computational resources, plus comprehensive internationalization.
Feb 3, 2025
- v2.1.2
Simple update adding support for Google's gemini-2.0-flash-exp model.
Dec 13, 2024
- v2.1.1
Bug fix release addressing multiple stability and compatibility issues across TTS, segmentation, and model support.
Dec 10, 2024
- v2.1.0
Adds custom terms, Deepseekcoder support, and local TTS capabilities using Ollama and Edge-TTS.
Dec 5, 2024
- v2.0.4
Adds Demucs configuration and improves audio quality, while fixing subtitle font size and 'All same length' errors.
Dec 3, 2024
- v2.0.3
Fixes alignment errors in voice generation and resolves audio reading issues during the whisper process.
Dec 2, 2024
- v2.0.2-deprecated
This deprecated release focuses on stability improvements, removing unstable installation scripts, and fixing audio recognition issues.
Dec 1, 2024
- v2.0.1-deprecated
A deprecated maintenance update that simplifies the installation process for Windows users by removing manual CUDA requirements.
Nov 27, 2024
- v2.0
A major version update introducing SiliconFlow integration (Qwen-72B LLM and Fish TTS) and a new OneKeyInstall script.
Nov 17, 2024
- v1.8.0
An update focused on code optimization and translation improvements, removing external API dependencies and adjusting transcription defaults.
Nov 13, 2024
- v1.7.1
A maintenance release adding MPS support, error retry mechanisms, and fixing bugs related to model loading and batch processing.
Nov 11, 2024