Skip to main content

​
Formats

Docker deployment already installs the FFmpeg dependencies required for narration video export. For source installs, install an FFmpeg build with libass / the ass subtitle filter first, for example brew install ffmpeg-full && brew unlink ffmpeg 2>/dev/null || true && brew link --overwrite --force ffmpeg-full on macOS or sudo apt-get update && sudo apt-get install -y ffmpeg libass9 on Ubuntu / Debian.

​
PPTX Export Panel

Regular PPTX export now opens a settings panel before generating the file. You can enable slide transitions and choose classic effects such as Fade, Page Turn, Push, Wipe, Split, Blinds, Checkerboard, and Clock. When multiple effects are selected, each slide randomly uses one of the selected effects.

​
Exported Files

The export tasks panel on the Slide Preview page lists export files already stored on the server for the current project. You can download PPTX, PDF, image archives, or narration videos again, or delete files you no longer need to free disk space. Deletion asks for confirmation first; after it succeeds, the file is removed from server storage and from the panel list. Export task history is scoped by project. Clicking Clear in one project removes only that project’s completed or failed tasks and leaves export history from other projects untouched. After a refresh, if a restored export task is no longer available on the backend, the panel marks it as failed and asks you to export again instead of leaving it stuck as in progress.

​
Narration Strategy

Narration video export now includes a final-step configuration panel so you can tune narration generation without changing the slide content itself.
  • Configure the speaker persona, target audience, speech tone, and core topic
  • Set the per-slide narration length to fit either shorter clips or deeper walkthroughs
  • Auto-generate missing narration while keeping the overall presentation flow connected from slide to slide

​
Aspect Ratio

Defaults to 16:9. You can change the ratio when creating a project or in Project Settings on the preview page. Supports 16:9, 4:3, 21:9, 1:1, 9:16, and more. Images must be regenerated after changing the ratio.

​
Editable PPTX (Beta)

The extraction process preserves font size, color, bold styling, text positioning, and table content. However, due to OCR accuracy limits and current model capabilities, complex layouts may have discrepancies from the original slide appearance. In the export dialog, you can enable Only Text Layers Editable. It is off by default. When enabled, Banana Slides generates a background that erases only detected text while preserving icons, images, charts, and other non-text visuals, then overlays the detected text as editable text boxes. VLM verification checks whether the background still contains text; if text remains, Banana Slides retries the erasure and keeps the candidate with the fewest missed text regions when all retries fail.
For best extraction results, configure BAIDU_API_KEY in your environment. See Configuration.

​
Icon Transparent Background

In Project Settings → Export Settings you can toggle Icon Transparent Background, which is enabled by default. When enabled, images classified as icons during editable PPTX export are processed via the local RMBG-2.0 model to produce transparent-background PNGs before being placed in the PPT, avoiding the icon’s original background clashing with the new slide background. Only elements classified as icons qualify (an OpenCV flood-fill heuristic runs on the ROI). Photos and illustrations keep the original rectangular crop to avoid mistakes.
Powered by local RMBG-2.0 ONNX inference on CPU. The ~512MB model is downloaded automatically on first use to ~/.cache/banana-slides/models/; set RMBG_MODEL_PATH to point at an existing local copy. If extraction fails for an individual icon, the system silently falls back to the original rectangular crop without affecting export.
Known limitation: icons rendered with a soft glow or anti-aliased halo against a colored slide background may retain a faint dark fringe or color cast along thin strokes after extraction, because edge pixels are originally a blend of the icon stroke and the slide background. Solid-color icons on plain backgrounds extract cleanly; complex glow effects on gradient backgrounds may need manual touch-up.

​
Page Selection

You can select specific pages to export rather than exporting the entire presentation. Enable Multi-select on the Slide Preview page, check the pages you want, then click Export. The export menu checks image readiness for the current export range. PPTX, PDF, Images, and Editable PPTX require every selected page to have a generated image; unfinished draft pages outside the selection no longer block exporting finished pages. For Narration Video, if the range still includes pages without images, you must explicitly enable Include pages without images in the video export dialog before Banana Slides exports placeholder frames.

​
Narration Video

Narration Video combines your slide images with AI-generated narration into a single MP4, complete with subtitles. Steps:
  1. Open a project on the Slide Preview page.
  2. Click Export → Narration Video.
  3. In the export dialog, configure:
    • Speaker persona — the speaking style (e.g. corporate executive, content creator).
    • Audience — who the narration is written for.
    • Tone — the emotional register of the script.
    • Voice — the TTS voice used for audio synthesis (see below).
    • Ken Burns effect — subtle zoom/pan motion on each slide (optional).
  4. Click Start Export. Progress is shown in the Export Tasks panel.

​
Voice Selection

Default (edge-tts): Free voices provided by Microsoft Edge, no API key needed. Options include Chinese (晓晓, 云希), English (Jenny, Guy), and Japanese (Nanami, Keita). ElevenLabs: Higher-quality, more natural voices. Requires an ElevenLabs API key configured in Settings (see Configuration → ElevenLabs). When ElevenLabs is enabled in Settings, the voice dropdown in the export dialog switches to ElevenLabs voices — Rachel, Bella, Adam, Josh, and more. The voice ID is handled automatically; you only pick a name.
ElevenLabs voices are English-optimized. For Chinese narration, edge-tts Chinese voices (e.g. 晓晓) generally produce better results.

​
Allow Partial Results

The Allow Partial Results option in Project Settings → Export Settings now applies consistently across export flows.
  • When disabled: the export fails immediately on critical gaps or errors, such as editable PPTX extraction failure, missing narration text for video export, or failure to generate usable narration audio.
  • When enabled: the system will continue whenever possible. For example, video export can fall back to silent clips for pages that do not have usable narration.