OpenCreator Releases

Jun 16, 2025

Hotfix for task ID errors with YouTube links and Alibaba Cloud speech recognition.

May 27, 2025

Adds OpenAI TTS, auto-save settings, auto-restart backend, and merges voice into final video.

May 26, 2025

Adds multi-file support, separate concurrency configs, and retry configuration.

May 6, 2025

Apr 25, 2025

This release fixes desktop subtitle orientation issues, resolves voiceover connection timeouts with Alibaba Cloud, and addresses empty text file outputs. It also enhances security by removing sensitive configuration details from logs and improves error handling for Large Language Model (LLM) output mismatches.

Apr 23, 2025

Adds support for WhisperCPP local transcription (Windows only), introduces Malay language support, and expands target languages to 101. The release also fixes dark mode visibility issues and updates the video downloader installation source.

Apr 19, 2025

Fixes critical desktop bugs including missing server configuration, audio download failures, loss of task progress upon tab switching, and potential API path errors.

Apr 13, 2025

Introduces English language support for the desktop version and resolves intermittent failures when writing subtitle files.

Apr 11, 2025

Apr 10, 2025

Releases the desktop version (currently in testing phase) with improved error handling, a result detection mechanism to re-run missed content, optimized task storage, and enhanced timestamp alignment algorithms.

Mar 30, 2025

Adds separate Whisper configuration within OpenAI settings, supports M-chip MacOS for local Whisper, introduces Russian language support, and fixes FasterWhisper bugs. Optimizes streaming for large model messages.

Mar 6, 2025

Feb 15, 2025

Feb 6, 2025

Adds subtitle embedding capabilities for link sources and Korean language support. Fixes vertical video subtitle rendering, empty audio segments, and single-language subtitle errors. Includes UI optimizations and proxy support for downloads.

Jan 22, 2025

Enables output of embedded subtitles (horizontal/vertical) and supports custom OpenAI model names/URLs. Adds text transcript output after task completion and fixes mixed language issues in dubbing.

Jan 14, 2025

Adds German and Turkish language support, fixes hyphen-related subtitle timing errors, Japanese transcription errors, and Aliyun transcription failures. Optimizes concurrency and timestamp alignment.

Jan 8, 2025

Adds Faster Whisper local model support (Windows and Linux), displays download progress and speed, and supports custom OpenAI base URLs. Improves error UI and logging.

Jan 3, 2025

This release introduces voice cloning capabilities, video upload support, and an Intel-specific macOS build. It also includes several fixes for download issues and dependency management.

Dec 30, 2024

Focuses on expanding translation capabilities with Alibaba Cloud integration and enhancing subtitle control with language options, positioning, and filtering.

Dec 26, 2024