返回资讯中心
外部精选
软件工程
#开发者实时流

ShortSmash – prompt-to-published short videos, 50-language dubbing, open source

ShortSmash is an AI video studio that takes one sentence — or today's trends — and ships a finished, captioned 9:16 short, then publishes it to YouTube, TikTok, Instagram, Threads, Bluesky, LinkedIn, Pinterest and X thr…

Hacker News 最新abicevoice12026/10/18 · 2026/10/1819 分钟阅读

以下正文同步自 Hacker News 最新,版权归原站所有,已转换为易读排版。

ShortSmash is an AI video studio that takes one sentence — or today's trends — and ships a finished, captioned 9:16 short, then publishes it to YouTube, TikTok, Instagram, Threads, Bluesky, LinkedIn, Pinterest and X through their official APIs. Script, voiceover, verified stock footage, karaoke captions, music ducking, trend harvesting, batch production, scheduling and comment-reply drafts, all in one CLI. And an MCP server, so AI agents can drive the whole factory.

shortsmash trends food # what's hot right now (free, no keys) shortsmash batch food --count 5 # turn the top 5 trends into 5 videos shortsmash serve # 🆕 web studio: http://localhost:8000 shortsmash agent "make a 30s reel about coffee and post it Friday at 6pm"

🖥️ ShortSmash Studio (web UI)

shortsmash serve launches a dark, fast studio in your browser — no build step:

Made end-to-end by ShortSmash — no hand-picked clips, no human editing. LLM script, neural voice, CLIP-verified stock footage, karaoke captions, ducked music bed.

"How Goats Made You Addicted to Coffee" — 49s, 1080×1920, made from one prompt:

The same video, re-voiced by shortsmash dub — Español · اردو · Roman Urdu. One project, every audience.

中文版 — the same video, fully re-voiced in native Mandarin (Piper huayan neural voice, not translationese), with Hanzi karaoke captions:

shortsmash serve — generate, browse trends, publish, and track stats from the browser:

Earlier demo: Hyderabadi biryani — the one that taught the pipeline to see.

Most text-to-video tools assemble clips blindly — whatever the stock API returns first goes in. That's why automated shorts have the infamous "stock-footage look": a burger in a biryani video, a robin in a cooking tutorial.

ShortSmash is the first open-source pipeline with eyes:

prompt ──▶ script ──▶ voice ──▶ visuals ──▶ captions ──▶ render ──▶ publish NVIDIA Edge-TTS Pixabay faster- FFmpeg official Gemini Piper CLIP whisper 1080x1920 APIs only OpenAI- (offline verified karaoke +faststart compat neural)

Script — NVIDIA NIM (free) → Gemini (free) → any OpenAI-compatible endpoint (OpenRouter, DeepSeek, local Ollama) → offline template. Writes a scroll-stopping script and a strict JSON edit plan, validated by pydantic. Second-person, punchy, 3–4s scenes.

Voice — Edge-TTS → Piper offline neural → gTTS fallback chain. Urdu/Hindi/Arabic voices included.

Visuals — free Pixabay footage, every clip verified by the vision gate. Prefer AI generation? Set visual_provider: custom with your own command (ComfyUI, Replicate, MiniMax…) — the gate still checks the result.

Captions — faster-whisper word timestamps → burned-in karaoke captions.

Render — FFmpeg: 9:16 smart reframe, transitions, hook + CTA overlays, ducked music, H.264/AAC faststart.

Publish — YouTube, TikTok, Instagram, Threads, Bluesky, LinkedIn, Pinterest, X. Official APIs only — no Selenium, no scraping, nothing that gets accounts banned.

Dub — shortsmash dub <slug> --lang ur re-voices any video in Urdu, Hindi, Arabic, Spanish, French, German or Portuguese — plus ur-roman / hi-roman for Roman-script captions ("Tum kaise ho?") with the native neural voice. Urdu captions render in proper Nastaliq calligraphy, right-to-left, with the karaoke highlight tracking the spoken word. Same verified clips, new native narration.

Analytics — shortsmash analytics pulls real views/likes/comments from YouTube's API. Numbers from the platform, not vanity metrics.

Trends — shortsmash trends <niche> harvests Google News + Hacker News (free, no keys). shortsmash batch turns the top trends into videos unattended.

Schedule — natural language ("Friday 6pm"), durable SQLite queue, retrying worker.

Engage — pulls recent comments, drafts warm replies, you approve each one with a tap. Nothing posts itself.

MCP server — python -m shortsmash.mcp_server exposes generate_video, get_trends, list_projects, project_status to Claude Code, Cursor, and any MCP client.

Resume — shortsmash resume <slug> picks up failed projects from the first incomplete stage instead of redoing everything.

How ShortSmash compares

ShortSmash MoneyPrinterTurbo OpenPost Postiz ShortGPT

Prompt → finished short ✅ ✅ ❌ (manual editor) ❌ ✅

Footage verification ✅ CLIP + Gemini ❌ n/a n/a ❌

Offline neural voice fallback ✅ Piper ❌ n/a n/a ❌

Audio safety gate ✅ ❌ n/a n/a ❌

Trend harvesting (free, no keys) ✅ ✅ ❌ ❌ ❌

Batch production ✅ ✅ ❌ ❌ ❌

Karaoke word-level captions ✅ ✅ ✅ ❌ ✅

Official publishing APIs ✅ 10 platforms ⚠️ Selenium for YT ✅ ✅ ⚠️

Multi-language dubbing ✅ 10 options (incl. Roman Urdu/Hindi, Chinese) ❌ ❌ ❌ ✅

Real analytics pull ✅ ❌ ❌ ✅ ❌

Web UI ✅ Studio ✅ ✅ ✅ ✅

MCP server ✅ ❌ ✅ ✅ ❌

Comment-reply drafts (human-approved) ✅ ❌ ❌ ❌ ❌

Resume failed projects ✅ ❌ n/a n/a ❌

License MIT MIT AGPL/Commercial MIT MIT

$0 to run ✅ ✅ self-host ✅ ✅

MoneyPrinterTurbo (129K★) is the most mature; OpenPost is the best manual workspace. ShortSmash is the most engineered AI-native pipeline — the only one that checks its own work.

No fake likes, comments, follows, shares, or stars. No botting, no "human-like" evasion of platform detection, no scraping or unofficial endpoints. That violates every platform's rules and gets accounts banned — and it doesn't work for real growth anyway. This boundary is architectural, not a policy note: the capability simply isn't in the codebase.

Windows (PowerShell) — paste this one line, done. It installs Python, FFmpeg, Git if missing, sets everything up, and puts ShortSmash Studio on your Desktop + Start Menu:

& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/hydope/shortsmash/main/install.ps1")))

Windows (CMD) — same thing, one line in Command Prompt:

curl -L -o "%TEMP%\rf-install.cmd" "https://raw.githubusercontent.com/hydope/shortsmash/main/install.cmd" && "%TEMP%\rf-install.cmd"

Linux / macOS / Git Bash (Windows) — one line, works everywhere including Git Bash on Windows:

curl -fsSL "https://raw.githubusercontent.com/hydope/shortsmash/main/install.sh" | bash

After install, launch ShortSmash Studio from the Start Menu / Desktop (Windows) or run shortsmash serve → open http://127.0.0.1:8000.

Prefer it manual? Download the repo and double-click install.bat (Windows) or run ./install.sh (Linux/macOS).

Needs Python 3.11–3.13 and ffmpeg (the PowerShell installer gets both for you). On Python 3.14+ the offline footage check is skipped automatically (torch has no build for it yet).

Make a video in the 🎬 Studio tab, then hit the 🚀 Publish tab to post it to 10 platforms (YouTube, TikTok, Instagram, X, Threads, Bluesky, LinkedIn, Pinterest, Facebook, Facebook Page) in one click — with per-platform setup status and dry-run safety.

Manual install, if you prefer it piecemeal:

pip install 'shortsmash[ai,voice,captions,trends,vision,mcp,youtube,x,schedule]' shortsmash init # guided setup: keys, voice, defaults shortsmash doctor # verify every dependency

Your first video (needs a free Pixabay key + any LLM key)

shortsmash new "coffee" --duration 30

Ride the trends

shortsmash trends ai --limit 5 shortsmash batch ai --count 3

Hands-free

shortsmash agent "make a 30s reel about the top AI trend and post it Friday at 6pm"

Free keys: Pixabay (footage) · Google AI Studio (Gemini LLM) · NVIDIA NIM (LLM). Or point openai_base_url at local Ollama and pay nothing at all.

docs/setup-youtube.md, setup-tiktok.md, setup-instagram.md, setup-x.md — per-platform OAuth

docs/trends.md — trend sources and scoring

docs/mcp.md — MCP server setup for Claude Code / Cursor

docs/visual-providers.md — plugging in AI visual generation

License

MIT — build whatever you want.

正文由 探How 从来源站点 RSS 同步,内容未经改写;遇到排版缺失或需要图片、视频时请以原文为准。

打开原文
去社区讨论 →