Zero-shot text-to-speech with voice cloning via IndexTTS2 (index-tts). Synthesizes speech from text using a user-provided reference audio for timbre. Use when the user wants TTS, text-to-speech, ?????? voice clone, ????, IndexTTS, IndexTTS2, or generating narration/voice lines from a reference WAV.
Reduces background noise in a single audio file using FFmpeg afftdn. Use when the user wants audio denoise, noise reduction, hiss removal, room noise cleanup, or SFX/voice cleanup before normalization.
Applies fade-in and fade-out at the start and end of a single audio file using FFmpeg. Use when the user wants audio fade, fade in/out, smooth attack/release, crossfade prep, SFX envelope shaping, or mentions afade.
Normalizes a single audio file to consistent LUFS loudness with true-peak limiting using FFmpeg. Use when the user wants loudness normalization, volume matching, unified audio levels, SFX/UI/BGM leveling, or mentions LUFS, true peak, loudnorm, or inconsistent game audio.
Standardizes a single audio file to 44100 or 48000 Hz and exports 16-bit PCM WAV using FFmpeg. Use when the user wants sample rate standardization, resample to 44.1 kHz or 48 kHz, WAV export at project sample rates, or mentions 44100, 48000, or PCM WAV conversion without loudness normalization.
Splits a single audio file into two segments (part 1 before the split point, part 2 after) using FFmpeg. Use when the user wants to split audio, divide a clip into two parts, cut at a timestamp, or separate intro from body.
Converts a single audio file to OGG Vorbis using FFmpeg for Godot-ready compressed assets. Use when the user wants to convert audio to OGG, transcode WAV/MP3/FLAC/AAC to OGG, export a Godot-ready OGG asset, or mentions Vorbis, libvorbis, or Godot audio import.
Converts a single audio file to WAV (PCM) using FFmpeg while preserving source quality. Use when the user wants to convert audio to WAV, transcode MP3/OGG/FLAC/AAC to WAV without downgrading sample rate or bit depth, or export a lossless WAV source asset.
Trims leading and trailing silence from audio files using FFmpeg. Use when the user wants audio trim, trim silence at start/end, remove leading/trailing silence, batch SFX cleanup, or voice dialogue preprocessing.
Adjusts audio file volume up or down using FFmpeg. Use when the user wants to change volume, boost or reduce loudness, attenuate or amplify SFX/UI/BGM, apply dB gain, raise/lower clip levels, or batch-adjust audio amplitude.
Normalizes asset filenames by splitting on common separators, stripping asset IDs and optional user strings from each segment, then joining with underscores (snakecase). Use when normalizing asset filenames, batch-renaming SFX/UI textures, file naming normalization, asset naming convention, slug normalization, or…
Generate single-line Conventional Commits messages by analyzing git diffs and repository history. Use when the user asks for commit messages, help writing commits, reviewing staged changes, or preparing a git commit.
Local circular region inpainting with LaMa (IOPaint). Uses IOPaint default InpaintRequest and mask handling. Use for 局部重�?/ 局部修�?/ inpaint when circle center and radius cx,cy,r are known.
Interactive Gradio UI to paint a region and remove solid key-color background (white / green / magenta) only inside that selection. Use when enclosed white islands remain after border/both keying, for localized 白底抠图, paint-to-erase chroma patches, or selective color-key cleanup before Godot sprite import.
Removes image backgrounds and exports transparent PNGs using rembg (U2Net / BiRefNet). Use when the user wants background removal, matting, cutout, 抠图, transparent sprites, alpha PNG export, or remove background from a game/UI asset.
Removes solid-color backgrounds (white, green #00FF00, magenta #FF00FF) from a single AI-generated image using color key and border flood fill �?not AI matting. Use when rembg over-removes foreground, for flat white/green/magenta backgrounds, color key cutout, 白底抠图, 绿幕, or chroma key before Godot sprite import.
Resizes a single image to explicit width and height using ImageMagick. Use when the user wants image resize, scale a sprite/texture, resize a UI asset or icon, or mentions ImageMagick resize �?target size must be specified before running.
Splits uniform sprite sheet grids into individual frame PNGs using FFmpeg crop. Use when the user wants to split sprite sheets, extract animation frames, divide grid images into cells, cut 4x4 or NxM sheets, slice tilesets, or prepare frames for background removal.
Converts image files to PNG using FFmpeg while preserving dimensions and alpha. Use when the user wants to convert images to PNG, transcode JPG/WebP/GIF/BMP/TIFF to PNG, export a game/UI texture as PNG, or mentions PNG conversion without background removal.
Trims invalid border regions (transparent or solid-color padding) from images using Pillow. Default crop preserves the source aspect ratio. Use when the user wants image trim, crop empty borders, remove transparent margins, trim white padding, auto-crop sprites, or tighten cutouts before Godot import.
Muxes per-shot storyboard video with Chinese and English voice-over by retiming video to match VO duration (setpts), writing Video-Chinese/ and Video-English/ (matched by shot id 01, 02, �?. Use when the user wants storyboard A/V mix, 分镜音视频合�? 配音合成, video retime to audio, Video-Chinese, Video-English, bilingual VO on…
Turns a storyboard shot (video prompt + narration) into a self-contained fullscreen HTML CSS animation for the browser. Analyzes VO/旁白, searches related facts and usage cues, then builds a rich layered stage (camera, subject, secondary UI, light, micro-detail) with Fullscreen API and Space-to-play. Use when the user…
Converts storyboard markdown (bilingual Chinese + English narration per shot) into speech audio via IndexTTS2 (same stack as ai-text-to-speech). Batch-writes WAVs under Chinese/ and English/ named by shot id (model loaded once), pads 0.4 s edge silence in place, then a speech-timeline.md and one concatenated SRT per…
Turns user materials into a shot-by-shot storyboard with bilingual narration (Chinese + English VO, both required) and AI video prompts per shot. When the user gives a target path (especially .md), write the full storyboard there — do not only print it in chat. Style and duration are free. Use when the user asks for…