🖼️ → 🎬 Slideshow Maker
Per-image audio
: upload audio files, one (or more) per image (matched by filename or order).
Per-image TTS (multiline)
: write blocks separated by
blank lines
; lines inside a block are spoken sequentially for that image.
TTS voices
: pick from
Coqui VCTK
multi-speaker voices (male/female) or use gTTS as a lightweight fallback.
Upload Images (multiple)
Drop File Here
- or -
Click to Upload
Image Order
Filename (A→Z)
Filename (Z→A)
Shuffle
Shuffle Seed (integer)
Seconds per Image (used when not syncing to audio)
↺
0.1
10
Width (px)
Height (px)
Sizing Mode
contain
cover
stretch
Background (for 'contain')
Narration mode
None
Single story
Per-image (files)
Per-image (TTS per line)
Per-image (TTS multiline per image)
Story (Single track narration)
Match video duration to narration length (single-story)
Per-image audio files (optional) — matched by filename or order
Drop File Here
- or -
Click to Upload
Sync image to audio duration (per-image modes)
Per-image TTS (one line per image)
Per-image TTS (multiline): blocks separated by blank lines; use 'speaker| text' to override
TTS backend
Default Voice (for Coqui)
Narration Gain (dB)
↺
-12
12
Create Video
Result
Tips
Multiline per image
: separate image blocks with a
blank line
. Within each block, lines are spoken in order.
Coqui per-line speaker
: prefix a line with
speaker| text
, e.g.,
p225| Hello there
.
Sync option
: turn it on to make each image stay up for the full duration of its own audio.