Turn your real product photos and confirmed product facts into a silent vertical MP4 photo montage, cover, editable shot plan and source ledger. Local rendering with Python, Pillow and FFmpeg; no paid video-generation API. Built for sellers and small agencies. Static photo montage with hard cuts, not generative footage, voice or music. Download for your own AI client; requires a computer and local tools.
Turn product information into production-ready short-video angles, hooks, scripts, storyboards, AI generation prompts, captions, CTAs, hashtags, and A/B/C variants—without fake claims or robotic ad copy.
Upload real photos of your product and get 15 to 30 second ad videos for TikTok, Reels, Shorts, feeds, Amazon and Shopify. ProductReel cuts the product out of your own photos and animates it: one benefit per screen, a price card with the old price struck through, a call to action, cuts on the beat. The product is never redrawn by AI, so its shape, logo and label stay as photographed. Six templates. You must own the rights to photos and music you upload.
Open-source CLI (MIT, 2k+ GitHub stars, Hacker News front page). Turn any video URL or local file into scene-aware keyframes plus a timestamped, speaker-labeled transcript your LLM can actually read. - Runs 100% on your machine, nothing is uploaded - Works with Claude, ChatGPT, Gemini or local models - URL videos reuse the platform's own captions, Whisper otherwise New in 0.10.5: Apple Silicon GPU transcription, about 6x faster on M-series Macs, same no-fake-captions gate.
One agent takes a short video from brief to a publish-ready pack: hook variants scored by visible rules, a timed shot list, per-shot prompts that repeat the same character and style text, captions and a cut list. Then a pre-flight QA checks claims, sources, real-person likeness consent, asset licenses, AI labelling, pacing and platform limits. Offline deterministic script. It does not generate video or promise views.
Watch the 60s film: https://youtu.be/sw6_8E-57w4 Pro adds to free claude-real-video: - camera & pacing (--motion) - voice emotion (--senses) - speaker labels (--speakers) - synced viewer (--viewer) - AI reports (--ai-report) New in 0.10.5: Apple Silicon GPU transcription. A 21-min talk in about a minute on an M4; music or silence never becomes fake captions. Built on open-source claude-real-video (2k+ GitHub stars, HN front page). Runs on your machine; only --ai-report uses your own API key.
Enter a topic and get a ready-to-post content set in minutes: 3 high-CTR titles, a 3-second hook, a full voiceover/shot-by-shot script, cover text, and targeted hashtags. It’s built on a library of proven viral structures, picks the best one for your topic, and checks length and restricted words against RedNote, TikTok. It’s made for solo creators, brand founders, and new accounts, and it fixes the two classic problems: not knowing what to post, and posting but getting no views.
Turn viral trends into personalized videos featuring your own face! Discover content ideas for TikTok, Instagram Reels, and YouTube Shorts, upload a reference photo, and create vertical videos with audio up to 30 seconds. Get AI-powered concepts, scripts, and video editing workflows designed for social media. Use only videos, images, and audio you have permission to use. Actual face-swapping and video export depend on connected tools.
Paste one published short's script plus its real analytics and get a retention autopsy of that exact video: a self-contained HTML report with the drop-off mapped second by second, a PASS / REWORK / REBUILD verdict against printed thresholds, a shot-by-shot cut list, and five hook variants.