Step-by-step instructions for each bot feature. Choose what you want to do:
Press the 🎬 Video button in the main menu or send the /video command.
Upload from 1 up to 5–30 photos (depending on your plan). You can send them as an album or one by one. JPG, PNG, and MP4 formats are supported.
The bot will display a settings menu:
To change the shot exactly where you want — insert a {scene} marker into the voiceover text between paragraphs. The bot syncs the photo change with the words, and the markers don't reach the voiceover (the voice never reads them).
{scene} — just switch to the next photo{scene:slide} — switch with a specific transition (slide, zoom, fade, circle…){scene:zoom:0.8} — a “zoom” transition lasting 0.8 secondsFirst shot about coffee {scene:slide} Second shot about dessert {scene:zoom} Third shot with the price — the bot makes three scenes with different transitions. Match the number of markers to the number of photos.Press ✅ Generate. The bot will process your request and send the final MP4 directly to the chat — usually within a few seconds.
Besides subtitles, you can burn your own captions/titles over the frame — manually or fully automatically.
TEXT | attributes | start-end (e.g. Hello | large yellow center pop | 0-3). Each caption has its own style, size, position, color and fade timing. The appearance animation is picked with the 🎬 button or in codes: pop, slide, type (typewriter).Press 📝 Subtitles in the menu or send /subtitles.
Upload a video file up to 500 MB (depending on your plan). MP4, MOV, AVI, and other common formats are supported.
Specify the spoken language in the video and the subtitles style — color, size, position, and animation.
The bot will return a ready-to-use MP4 with hardcoded ("burned-in") subtitles — they are visible on any device without extra configurations.
Press 🎙️ Transcription in the menu or send /transcription.
MP3, WAV, OGG, MP4, and most common formats are supported. Maximum duration depends on your plan (from 15 min on Free to 20 hours on Pro+).
The bot will return the transcription as a TXT file (plain text) and an SRT file (with timecodes for subtitles).
Press 🔊 Dubbing in the menu or send /dubbing.
Upload the video containing the voice you want to replace. Time limits for dubbing range from 1 min on Free to 5 hours on Pro+.
3 modes are available:
The bot will return the video with a new voice and balanced audio tracks.
Press 🗣️ Voiceover in the menu or send /tts.
Paste text in any language. Character limits range from 5,000 on Free to 1,000,000 on Pro+.
Voices from Google, Gemini 2.5, Azure, Edge TTS, HuggingFace, and ElevenLabs (Pro+) are available. You can adjust speed and pitch.
The bot will send the completed audio file — ready to use in any video editor.
Press ✂️ Remove Pauses in the menu or send /pauses.
Processing limit ranges from 5 min on Free to 10 hours on Pro+.
By default, the bot uses optimal settings. If needed, you can specify the silence threshold manually.
The bot will return the video without pauses — usually 20–40% shorter than the original.