An intelligent timeline subtitle tool with local AI speech recognition that automatically generates perfectly synchronized subtitles from audio.✅ One-click audio-to-subtitle conversionUses locally deployed speech recognition engine to automatically convert audio into precisely timed subtitlesSupports multiple languages (English, Chinese, Japanese, etc.), though currently only English and Chinese have been tested✅ Efficient content creationCustomizable text segmentation for optimal subtitle formattingBatch processing support to significantly improve workflow for cutscenes and dialogue systems✅ Seamless Timeline integrationNative Timeline editor support - no need for third-party softwareCurrently Supported FeaturesGenerates three subtitle track types: TextMeshProUGUI, TextMeshPro, and Legacy TextCustomizable speech recognition models (requires manual model file downloads)Configurable speech recognition promptsBatch processing for multiple selectionsSubtitle delay adjustmentPredefined punctuation rulesAutomatic line breaks based on:Maximum character lengthPlanned FeaturesSRT export formatProofreading tools and interfaceAudio clip-level controlsPost-generation adjustmentsAboutThis resource includes third-party components licensed as follows:whisper.unity - MIT licenseOpenAI Whisper and models - MIT licenseTTSMaker sample audio - Commercial licenseFor complete license terms, please refer to the package: /Notices.txt
