
# Search Your Library by Meaning, Not Filenames

Everyone has the same problem with their media library: you *know* the photo exists, but you have no idea what it's called. Was it `IMG_4821.jpg`? Was it in the Italy album or the one from the conference? You end up scrolling for ten minutes looking for "that shot of the red bicycle against the blue wall."

Today we're shipping the fix. **Semantic search** lets you find media by describing what's in it. Type "red bicycle against a blue wall" and you get the photo — even though nobody ever typed those words as a caption, a tag, or a filename.

This post covers how it works, the new **AI Search Index** controls in album settings, and exactly what it costs.

---

## What "semantic" actually means here

A normal search matches text. If you search "dog," it finds files with "dog" in the name or description, and misses the photo of your golden retriever labeled `IMG_0042.jpg`.

Semantic search matches *meaning*. Under the hood, every piece of media gets turned into an **embedding** — a list of numbers that captures what the content is about. Your search query gets turned into an embedding too, and we find the media whose meaning sits closest to your query.

The result: searching "celebration" surfaces birthday parties, fireworks, and a champagne toast — none of which contain the literal word "celebration." It understands the concept, not just the characters.

We use Google's `gemini-embedding-2` model for this, and one detail makes it especially powerful: it's **multimodal**. It can read the *pixels* of an image directly, placing photos and text into the same shared "meaning space." That's why a text query can find an untagged photo — the image itself was understood, not just a caption someone wrote about it.

---

## How indexing works (and why media types differ)

Before search can find something, that item has to be indexed. Here's what happens per media type:

- **Photos** are embedded directly from the image itself. If a photo already has an AI description, we fold that text in too for an even richer match — but a photo with no description at all still becomes fully searchable, because the model reads the image.
- **Videos and audio** are different. The embedding model can't watch a long clip, so these first get a short AI-generated **summary** of their content. That summary text is then embedded. If a video already has a description, we skip straight to embedding it.

The upshot for you: photos are instant to index, while videos and audio take an extra step to "watch and summarize" first. Both end up equally searchable.

---

## The AI Search Index, right in album settings

We used to nag you with a banner above every album: *"12 images missing AI description."* It was in your face, and worse, it asked you to commit to indexing without telling you what it would cost. That banner is **gone**.

In its place, every album owner now has an **AI Search Index** section inside **Album Settings** (it sits between Album Sharing and the Danger Zone). It's calm, on-demand, and honest about cost. When you open it, you'll see one of a few states:

- **All indexed** — a green checkmark and "All media in this album is indexed for semantic search." Nothing to do.
- **Work pending** — a clear breakdown of what's left, like *"12 photos · 3 photos with descriptions · 1 video needs a summary first,"* an estimated cost in dollars, and a **Generate** button.
- **In progress** — "Indexing already in progress. Batch jobs can take a few minutes to a few hours," with a Refresh link to check back.

You decide when to index, album by album (or your whole library at once). Nothing happens until you click Generate.

> **Note:** This feature is live on the **web app** today. The 5AM iOS app isn't released yet, but the same AI Search Index surface is built and waiting for it.

---

## What it costs

This is the part most tools hide. We put it front and center, because the honest answer is: **for almost everyone, it's a rounding error.**

Indexing runs on your own Gemini API key, and we route the bulk indexing through the **Gemini Batch API — which Google prices at half the standard rate.** The cost line in album settings even annotates this: *"Gemini Batch API rate, 50% of standard."*

Here's the breakdown of what each piece costs, using current Gemini pricing (all at the discounted batch rate):

- **Embedding a photo or description** — `gemini-embedding-2` at **$0.10 per million tokens**.
- **Summarizing a video/audio clip first** — `gemini-2.5-flash` at **$0.15 in / $1.25 out per million tokens**.

To put that in real numbers:

- **Photos are effectively free to index.** A photo embed is about 100 tokens. At batch rates, that's on the order of **$0.0001 per photo** — roughly **a hundredth of a cent**. Indexing a 1,000-photo album costs around **ten cents**.
- **Videos and audio cost a little more** because they need a summary step first (and that summary runs at standard Flash rates, since it goes through our video service). Figure somewhere in the **$0.001–$0.005 per clip** range.

The estimate you see in album settings is computed from these exact numbers before you click anything — no surprises on your bill.

For the official, always-current pricing straight from Google, see the **[Gemini API pricing page](https://ai.google.dev/gemini-api/docs/pricing)**.

---

## Built to be safe to re-run

A few things we sweated so you don't have to:

- **It never re-indexes what's already done.** Each item is fingerprinted by its content. Re-click Generate on an album that's fully indexed and it'll simply say "nothing to do" — no duplicate work, no duplicate cost.
- **It only re-indexes what changed.** Edit one photo's description and re-run, and only that single photo goes back through.
- **It survives crashes.** Batch jobs can run for hours on Google's side. Our system tracks every job in the database and resumes cleanly after any restart, so you never lose an indexing run or get charged for a phantom one.

---

## How to try it

1. Open any album you own and go to **Settings**.
2. Scroll to the **AI Search Index** section.
3. Review the breakdown and the estimated cost.
4. Click **Generate**. (If you haven't saved a Gemini API key yet, you'll be prompted once.)
5. Give it a few minutes for photos — videos may take longer while they're summarized — then use the album's search box and describe what you're looking for.

That's it. Start with one album, watch a search that should be impossible suddenly work, and then index the rest of your library knowing exactly what it'll cost.

---

## Prefer the terminal? Use the CLI

Everything above is also available from the [5am CLI](/cli) — handy for scripting, bulk work, or wiring search into your own tools.

**Index an album** (same batch-API path as the web UI, at the discounted rate):

```sh
5am albums generate-summary <albumId>
```

It's async and idempotent — re-running on an already-indexed album submits nothing and just reports "Already indexed — nothing to do."

**Search by meaning:**

```sh
5am media semantic-search "sunsets at the beach"
5am media semantic-search "wedding photos" --album <albumId> --limit 20
```

Both need a Gemini key set once with `5am keys set gemini <key>` (the index call embeds your media; the search call embeds your query). Results come back as JSON by default — add `--pretty` for a readable table.

**[Open your albums →](/albums)** · **[Get the 5am CLI →](/cli)**


5AM's new semantic search lets you find photos and videos by describing what's in them — and a redesigned AI Search Index in album settings shows you exactly what it costs before you index a single file.

Search Your Library by Meaning, Not Filenames


# Introducing Podcast Studio

At 5AM, our goal has always been to build a unified hub for creative expression. We started with photo storage, moved into AI-assisted image generation, and brought it all to your terminal with the `5am` CLI. 

Today, we're expanding into sound and video with the release of **Podcast Studio**—a self-contained tool that turns text, web pages, Hacker News threads, RSS feeds, or user-uploaded media into a fully produced, multi-voice "radio talk show" podcast. And when you're ready to share your show on platforms that demand video, you can wrap it with an animated waveform overlay—and timestamp-synced burned-in captions—using the companion `5am` CLI.

The feature is live right now: visit the web app at **[/podcast](/podcast)** or update your CLI to get started.

---

## Direct in the Browser, Powered by Your Gemini Key

Most podcast generation tools run heavy processing pipelines on the server, which introduces high latency and expensive subscription gates. We built Podcast Studio differently: **everything runs client-side in your browser.**

Your script generation, text-to-speech synthesis (TTS), and audio transcription hit Google's API directly using your own Gemini API key. Our backend never proxies your API key, never sees your audio segments, and never bills you for generation. For anonymous guests, your key is requested lazily only when you click generate; logged-in users can save their key securely to their profile.

By keeping the heavy lifting local to the browser, we've enabled a level of customization and interactivity that server-bound apps cannot match.

---

## How It Works: The Web Experience

When you visit **[/podcast](/podcast)**, you’ll step into a dark-themed virtual recording studio designed to handle everything from intake to final export.

### 1. The Intake Board
Choose from five distinct modes to seed your episode:
- **Text & Files:** Paste a text draft or script.
- **URL & RSS Feeds:** Provide any website link or podcast feed. (Our server assists behind the scenes with a secure, CORS-compliant fetch to keep your browser safe).
- **Hacker News:** Browse and pull top stories directly into your feed.
- **Media Upload:** Upload a local audio/video file; Gemini will transcribe it on the fly to use as the source material.

Before generating, you can customize your **Cast**. Add anywhere from **2 to 8 speakers** (a host and up to 7 callers), assign them custom names, write character descriptions to guide their talking points, and select their voices from **30 prebuilt Gemini TTS voices** (such as *Zephyr · Bright* or *Charon · Informative*).

### 2. Intelligent Scripts & Vocal Performance
When you hit "Generate", `gemini` analyzes your intake material and generates a radio script in a structured JSON schema mapping back to your custom cast names. 

We feed this script to `gemini-text-to-speach` in the browser, segment by segment. To make the dialogue sound authentic, the script generator injects inline performance cues like `[laughs]`, `[sighs]`, or `[whispers]`. The TTS model acts on these instructions to generate natural pauses and emotional vocal inflection, rather than reading them aloud.

### 3. The Studio Dashboard
Once your episode is ready, the interface transitions to the **Studio View**:
- **Tape Deck:** A retro animated cassette tape that spins during playback, bordered by a glowing circular progress ring.
- **Teleprompter:** A scrolling script highlighting each spoken line in real time. Want to change what a speaker said? Click the edit pencil on any segment, rewrite their line, and press `Ctrl/Cmd + Enter`. The studio immediately invalidates the cache for that segment and synthesizes a new audio clip on the fly. You can also click any segment to jump playback directly to that line.
- **On-Demand Cover Art:** Click to generate custom 1:1 square album art using `gemini-image-generation` based on your episode's title and summary. The artwork displays on the cassette reels and is ready to download.

When you're happy with the edit, click **Download WAV** to compile all segments locally into a single audio file, or **Save to Album** (for logged-in creators) to add the WAV directly to your 5AM media library.

### 4. Timestamp-Synced Transcripts

Alongside the WAV, the Export panel lets you download a **transcript in three formats—`.vtt`, `.srt`, or `.json`**. These aren't rough approximations: the timestamps are derived from the exact byte position of each segment in the compiled audio (24&nbsp;kHz mono PCM, so every 48,000 bytes equals one second), which makes them **sample-accurate against the WAV you just downloaded.**

That precision is what makes the next step possible. The `.srt`/`.vtt` files drop straight into the CLI as burned-in captions, and the `.json`—a structured list of `{ speaker, text, startMs, endMs }` cues—is perfect for programmatic workflows like timing AI-generated b-roll scenes to the dialogue.

---

## From Audio to Video: The CLI Integration

Audio files are perfect for RSS feeds, but platforms like YouTube, Instagram, X (Twitter), and TikTok require video. 

To bridge this gap, the `5am` CLI includes the **`media visualize`** command. It takes your downloaded WAV file and cover art and turns them into a high-definition H.264 MP4 video featuring a dynamic, animated audio waveform.

### Quick Example

If you have downloaded `episode.wav` and your generated cover art `cover.png` from the Podcast Studio, run the following command in your terminal:

```sh
5am media visualize episode.wav \
  --cover cover.png \
  --output episode.mp4
```

This renders a 16:9 widescreen video with your cover art letterboxed on a clean slate-950 canvas and a Winamp-style scrolling waveform across the bottom quarter.

### Burn In Your Transcript as Captions

Remember the transcript you downloaded from the Studio? Pass it with **`--subtitles`** and the CLI burns it in as captions, positioned just above the waveform strip:

```sh
5am media visualize episode.wav \
  --cover cover.png \
  --subtitles episode.srt \
  --output episode.mp4
```

Because the transcript timestamps are sample-accurate against the WAV, the captions stay perfectly in sync with the audio—no manual nudging. The CLI accepts both `.srt` and `.vtt`; styling and positioning are handled for you, legible white-on-translucent text on the dark canvas.

### Advanced Visualizer Controls

The CLI visualizer is highly configurable depending on your target platform:

* **Aspect Ratios (`--aspect`):** 
  * `16:9` (default) for YouTube
  * `1:1` for Instagram and grid feeds
  * `9:16` for vertical videos (TikTok, Shorts, Reels)
* **Visualization Styles (`--style`):**
  * `showwaves` (default): Classic oscilloscope lines
  * `showfreqs`: Frequency spectrum bars
  * `showcqt`: Constant-Q transform color band
  * `showspectrum`: Waterfall spectrogram display

To generate a vertical video with frequency bars and burned-in captions for TikTok, you can run:

```sh
5am media visualize episode.wav \
  --cover cover.png \
  --subtitles episode.srt \
  --aspect 9:16 \
  --style showfreqs \
  --output tiktok-reels.mp4
```

*Note: The CLI visualizer requires a local installation of `ffmpeg`. If you run the command without authenticating (`5am login`), your video will include a small "Powered by 5AM" watermark in the bottom-left corner.*

### Going Further: AI B-Roll in One Command

Want more than a waveform? The repo ships a one-shot wrapper, **`scripts/podcast_to_video.py`** (stdlib-only Python, runs anywhere), that automates the whole pipeline. In its default mode it measures your audio, generates enough short **Veo** b-roll clips to cover it, stitches them together, lays your podcast audio on top, and—with `--subtitles`—burns in your transcript. Give it your transcript and it even has Gemini write per-scene prompts so the visuals track the conversation:

```sh
# AI-generated b-roll behind your episode, with captions
python3 scripts/podcast_to_video.py -i episode.wav -s episode.srt -a 9:16
```

Prefer the waveform look without writing the `media visualize` flags yourself? The same script does that too with `--visualize --cover cover.jpg`. One script, both paths.

---

## Ready to Broadcast?

Whether you're looking to summarize long documents into conversational audio, turn blog posts into podcasts, or share your terminal commands as animated talk shows, Podcast Studio makes the process seamless.

1. Head over to **[/podcast](/podcast)** to record your first show.
2. Enter your Gemini API key (or save it to your profile).
3. Tune the cast, edit the script, and download the master WAV plus a `.srt`/`.vtt` transcript.
4. Run `5am media visualize --subtitles episode.srt` to render a captioned video for social media.

We can't wait to hear what you create. If you have feedback on voice quality, custom scripts, or CLI options, reach out to us!

**[Try Podcast Studio →](/podcast)** or **[Get the 5am CLI →](/cli)**


Turn text, web pages, and RSS feeds into multi-voice podcasts right in your browser. Edit scripts in real time, generate custom cover art, export timestamp-synced transcripts, and render animated videos with burned-in captions using the 5am CLI.

Introducing Podcast Studio: From Text to Multi-Voice Radio Shows and Videos


# Meet 5AM

If you ship media for a living, your day probably looks something like this: raw footage on one drive, renders on another, references in Drive, mood boards in Notion, a paid model in one browser tab, an editor in another, a host somewhere else, and an invoice you keep meaning to send. The work is creative. The plumbing isn't.

5AM is the plumbing — collapsed into one place. Store your library, edit it, generate new material with AI, share it with clients, and get paid for it. Browser or terminal, your choice. Here's the actual tour.

## One library, any format

Albums hold photos, videos, and audio. Upload from the web, drag a folder onto the CLI, or let an AI agent push renders in overnight. Either way, everything lands in the same library with thumbnails, EXIF, and AI-generated descriptions you can search semantically — "dog on a beach at sunset" finds the file, even if you named it `IMG_4421.HEIC`.

Video doesn't have a file-size ceiling. We use presigned uploads straight to cloud storage, so your browser isn't reading a 12 GB master file into memory and praying. Quotas are visible and enforced up front — no surprise overages.

## Editing that doesn't fight you

The image viewer is built for the gesture you actually use: pinch to zoom, drag to pan, double-tap to jump in. Crop has the aspect ratios you ship to (1:1, 16:9, 9:16, 4:3, 3:4, or free). Tone curves run on the GPU. Filters, text overlay, the usual basics — fast.

The interesting one is **Magic Eraser**. Tap the thing you want gone, the server runs custom AI model to mask it, Imagen fills in what should have been there. Object disappears. The heavy model work happens server-side, so your browser stays responsive while it runs.

Video gets a timeline editor with the processing pipeline pushed into Web Workers so the UI doesn't stutter. Trim, cut, join, mute, replace audio. `.mov` files auto-convert to `.mp4` on upload so nothing breaks on the way out. 

## AI Studio, no lock-in

Generate images and video from prompts using the models you'd pick anyway: Gemini 2.5 Flash Image, Imagen 3, Imagen Ultra, DALL·E 3, Veo 3, Veo 3.1.

The angle that matters: **bring your own API keys.** We don't mark up token usage. Plug in your Google or OpenAI credentials, generate at provider rates, and the output drops straight into your library — ready to crop, color, or composite into the next thing.

## The CLI

If you've automated anything, you'll like this part. The `5am` CLI is a single Go binary, cross-platform, JSON by default. It's built to be piped — into `jq`, into shell loops, into AI agents like Claude Code or Gemini CLI.

```sh
# Back up a shoot and print the share link
ALBUM=$(5am albums create --name "Shoot $(date +%F)" | jq -r .id)
5am media upload ./renders -r --include '*.jpg,*.mp4,*.mov' \
  --album "$ALBUM" --concurrency 8
echo "https://5am.app/album/$ALBUM"
```

Three lines, no GUI. Uploads parallelize with a configurable worker pool, big videos use presigned URLs under the hood, progress streams to stderr so your JSON pipes stay clean. 

There's a longer write-up if you want it: [Introducing the 5am CLI](/blog/introducing-the-5am-cli).

## Share it. Sell it. Keep the money.

Three ways to share an album:

- **Direct** — invite collaborators by email with view, comment, or contribute access. Good for clients and teams.
- **Public link** — share a URL, optionally protected by a token. Good for portfolios and one-off handoffs.
- **Paid access** — set a price, share the link, get paid when someone buys access. Good for selling presets, stock packs, cuts, or whole collections.

Payments run through Stripe, and payouts go to your bank via Stripe Connect. You set the price, you keep the money. We're not a marketplace taking a cut on top of the card fees.

## Pricing

Everything you need to get started — library, editing, AI Studio with your own keys, and the CLI — works on the **Free tier**, which includes 10 GB of storage at no cost. 

If you need more space or want to unlock features like AI characters, check out all the details on our [pricing page](/pricing).

## Where to start

If you want to poke around, [sign in](/login) and create your first album in about thirty seconds. If you'd rather start from the terminal, the [CLI page](/cli) has install one-liners for macOS, Linux, and Windows.

If you build something interesting, we'd like to see it.


Store, edit, generate, and sell your media from one place — browser, terminal, or AI agent. Here's what 5AM actually does.

Meet 5AM: A Media Hub Built for Creators Who Move Fast


# Meet AI Characters: Your Personal Creative Team

A blank chat box can feel like staring at an empty page. You know what you want, but every time you start a new conversation you have to re-explain who you are, what you're working on, and how you like things done. That gets old.

AI Characters are 5AM's answer. Each character is a small, focused AI assistant you build once and reuse forever. You give it a name, a personality, an area of expertise, and a way of working — and from then on, talking to it is like calling a colleague who already knows the project.

And when one character isn't enough, the **Playground** is where a whole team of them collaborate on a task together.

## What is an AI Character?

Think of an AI Character as a saved version of "the perfect assistant for this one job".

You decide:

- **What it knows.** Its expertise areas — photography, copywriting, finance, gardening, whatever you want.
- **How it talks.** Friendly and casual, or formal and precise. Quick one-liners, or thorough explanations.
- **What it values.** Honesty, creativity, brevity. Quirks like "always asks one clarifying question first" or "loves analogies".
- **What it remembers.** Characters with memory enabled remember past conversations, learn from your feedback, and pick up your preferences over time.
- **What it can do.** Skills like reading albums, generating images, or running tools — granted per character so each one only does what it should.

That last part matters. A "Travel Photographer" character that can pull from your travel albums and generate images is a completely different tool from a "Brand Voice Editor" that only works with text. You don't want them mixed up, and you don't want to re-explain the difference every time.

## Why bother? Just chat with ChatGPT

Fair question. Here's the difference.

**A regular AI chat is a stranger every time.** It doesn't know you, doesn't know your work, and forgets the conversation the moment you close the tab.

**An AI Character is a teammate.** It knows your style because you set it up that way. It knows your library because it has access. It remembers what you discussed last week. And when you give it a thumbs-down on a response, it actually *learns* — that feedback shapes how it answers next time.

You build a character once. Then for every recurring task that fits its job description, you skip the setup and go straight to the work.

## The Playground: when one character isn't enough

Some tasks are bigger than any single specialist. Writing a launch announcement isn't just copy — it's research, a draft, an image, a social-media variant, and a tone check. That's five different jobs.

The Playground is where multiple characters collaborate. You start a session with one **orchestrator** — a character whose job is to coordinate. You hand it the goal in plain English. It then:

1. **Reads what you want.** Breaks the task into smaller pieces.
2. **Picks the right specialist for each piece.** Either from your existing characters, or it'll suggest creating a new one.
3. **Delegates.** Each specialist works on its piece.
4. **Gathers everything back.** The orchestrator assembles the results into the final answer.

You watch it happen in real time. You can approve, redirect, or jump in at any step. It's less like prompting an AI and more like running a small team.

## Use cases that get exciting

Here's where this stops being abstract. Some real workflows people are building:

### A weekly newsletter, almost on autopilot

- **Researcher** character pulls interesting news from URLs you drop in.
- **Editor** character drafts a first pass in your voice.
- **Headline Writer** character produces three options.
- **Visual Storyteller** character generates the hero image from your photo library.

You start a Playground session every Monday morning, paste a few links, and have a draft in fifteen minutes instead of three hours.

### Photo library curation that actually happens

- **Photo Critic** character reviews a recent album and flags the keepers.
- **Caption Writer** character drafts captions for the keepers in the voice you set.
- **Tagger** character adds searchable tags so future-you can find them.

A weekend trip's worth of photos — usually a backlog that lives on your phone forever — becomes a properly archived album in one session.

### A personal brand that doesn't sound like a brand

- **Brand Voice** character knows exactly how you write. You set it up by giving it samples of your past work.
- Every blog post, social post, and product description goes through it. Drafts come back sounding like *you*, not like generic marketing copy.

This is where memory and feedback compound. After ten interactions you've trained a character that's hard for a stranger to replicate, even with the same prompt.

### Solo founders running a one-person company

- **Customer Reply** drafts responses to support emails.
- **Finance Helper** turns your bank-statement notes into categorized expenses.
- **Investor Update** writes the monthly progress email.

Each one is a separate character with a separate scope. None of them can step on another's lane. You stay in control; the volume of busywork drops.

### A creative writer who experiments

- **Plot Doctor** reads your draft and suggests where the pacing sags.
- **Dialogue Punch-up** rewrites a scene to make characters sound more distinct.
- **Style Mimic** can imitate a specific author's prose pattern when you want to try something out of your comfort zone.

These three characters don't compete; they cooperate when you put them in the Playground together with a chapter and ask for feedback.

## How to start

You can build your first character in about three minutes:

1. Go to **AI Characters → New Character**.
2. Give it a name and pick a type: text, visual, or hybrid.
3. Describe how it talks and what it's good at.
4. Optionally write a system prompt, or click **Generate with AI** to draft one from your settings.
5. Save and chat with it.

For Playground:

1. Build a character and turn on **Orchestrator Mode** in its Settings tab.
2. Go to **AI Playground → New Session**.
3. Pick the orchestrator and give it a task.
4. Watch the team work.

## A note on what this is *not*

AI Characters aren't a magic "do my work for me" button. They're tools that get more useful the more you shape them. The first version of any character is fine. The fifth version — the one you've corrected, refined, and given memory time to settle — is the one that actually saves you hours.

Treat them like apprentices, not oracles. You'll get a lot more out of them.

If you've been waiting for a way to make AI feel less like a slot machine and more like a team you trust, this is it. Go build a character. See what changes.

[Open AI Characters →](/ai/characters)

[Try the Playground →](/ai/playground)


Build AI characters with their own personalities, expertise, and skills — then put them to work on real tasks in the Playground. Here's why it matters and what you can build.

Meet AI Characters: Your Personal Creative Team


# Introducing the 5am CLI

The web app is great when you want to browse and edit. But sometimes you have ten thousand photos on a backup drive, a script that needs to drop renders into an album every night, or an AI agent that should be able to manage your media library on your behalf. For those moments, opening a browser is the wrong tool.

Today we're shipping the **`5am` CLI** — a single Go binary that gives you the full Media Hub from your terminal. It's JSON-by-default, exit-code-aware, and built so the next thing you pipe its output into can be `jq`, a shell loop, or an AI agent.

## What you can do

```sh
# Albums
5am albums list
5am albums create --name "Trip 2026"

# Upload a whole directory recursively, filtered to images and videos
5am media upload ./photos -r --include '*.jpg,*.mp4' --album <id> --concurrency 8

# Download an entire album to a local folder
5am albums download <id> --output ./trip --concurrency 8

# Generate media from a prompt
5am media generate image --prompt "a cybernetic owl at dawn" --output owl.png
5am media generate video --prompt "a flowing river in autumn" --output river.mp4
```

That's the surface area. Underneath, the CLI uses presigned upload URLs (no client-side size limits on video), parallelizes uploads and downloads with a worker pool, and streams progress to stderr so you can pipe results without garbage in your JSON.

## Built for scripts

A few decisions we made deliberately:

- **stdout is JSON.** Every command returns a parseable manifest. `--pretty` is opt-in for humans.
- **stderr is progress.** Per-file upload and download messages go here so `5am ... | jq` stays clean.
- **Exit codes mean something.** `2` for auth, `3` for validation, `4` for network, `5` for server. Branch on them in your scripts instead of grepping log lines.
- **`--yes` skips prompts** so destructive ops can run unattended.

A typical "back up this directory to a new album" script ends up being three lines:

```sh
ALBUM=$(5am albums create --name "Backup $(date +%F)" | jq -r .id)
5am media upload ./incoming -r --include '*.jpg,*.mp4,*.mov' --album "$ALBUM" --concurrency 8
echo "Done — view at https://5am.app/album/$ALBUM"
```

## AI characters from the command line

The CLI also unlocks the parts of 5AM that work best when something else is driving — your **AI Characters**.

Every character has its own scoped CLI token (read / write / admin), its own enabled skills, and its own optional webhooks. From the terminal you can:

```sh
# Spin up a character with a profile, skills, and scopes
5am characters create \
  --name "Pico" \
  --communication-style "friendly and concise" \
  --skills get_album_images,fetch_media \
  --scopes read,write

# Chat with it — one-shot, REPL, or with persistent history
5am characters chat <id> "what's on my schedule today?"
5am characters chat <id> "create a summary of my recent uploads" --history /tmp/chat.json

# Or let an external system drive it via webhooks
5am characters webhooks create <id> --url https://example.com/hooks/5am --events chat,skill
```

Skills are scope-checked at execution time, so a `read`-only character can't suddenly delete an album because the prompt told it to. And `--active false` is a kill switch that disables the character's token at the platform layer in seconds.

## Built for AI agents

The CLI ships with a `SKILL.md` file that drops straight into Claude Code, Gemini CLI, or any tool that follows the [Agent Skills](https://agentskills.io) standard. Once installed, an agent can recognize prompts like "upload these photos to a new album" or "show me what's in my Trip 2026 album" and reach for the `5am` binary on its own — no glue code required.

If you've ever wanted an agent that can actually manage a media library instead of just talking about one, this is the missing piece.

## Local skills, real local access

When you `chat` with a character, the CLI gives it a set of **local skills** that run on your machine — read a file, write a file, run a shell command, process video with FFmpeg, generate an image and save it directly to a path you choose. Destructive operations (`rm`, etc.) prompt for approval; you can pass `--auto-approve` if you want the character to work autonomously on safe operations.

The result is an agent that can do real work: "render a thumbnail from `intro.mp4` and upload it to my Trip album," "transcribe the audio from `meeting.wav` and save the text," "generate ten variations of this prompt and save them to `./variants/`."

## Getting started

Prebuilt binaries live at **[cli.5am.app/cli/latest/](https://cli.5am.app/cli/latest/manifest.json)**. Pick the one for your machine:

```sh
# macOS (Apple Silicon)
curl -L -o 5am https://cli.5am.app/cli/latest/5am-darwin-arm64
chmod +x 5am && sudo mv 5am /usr/local/bin/

# macOS (Intel)
curl -L -o 5am https://cli.5am.app/cli/latest/5am-darwin-amd64
chmod +x 5am && sudo mv 5am /usr/local/bin/

# Linux (amd64)
curl -L -o 5am https://cli.5am.app/cli/latest/5am-linux-amd64
chmod +x 5am && sudo mv 5am /usr/local/bin/

# Linux (arm64)
curl -L -o 5am https://cli.5am.app/cli/latest/5am-linux-arm64
chmod +x 5am && sudo mv 5am /usr/local/bin/

# Windows (PowerShell)
Invoke-WebRequest https://cli.5am.app/cli/latest/5am-windows-amd64.exe -OutFile 5am.exe
```

Then mint a token in the web UI (**Settings → CLI Access Tokens → Generate**) and log in:

```sh
5am login
5am whoami        # confirm
5am albums list
5am account --pretty
```

Want an agent to drive the CLI for you? The companion **[SKILL.md](https://cli.5am.app/cli/latest/SKILL.md)** drops straight into `~/.claude/skills/5am/SKILL.md` (or your Gemini-CLI equivalent).

Full installation instructions, integrity-verification, all download links, and the agent skill file live on the **[CLI page](/cli)**.



If you're scripting against the CLI and you hit something rough, let us know — early adopters shape the roadmap more than anyone else.

Welcome to the terminal. **[Get the CLI →](/cli)**


Upload, organize, and generate media without leaving the command line. Built for scripts, automations, and AI agents.

Introducing the 5am CLI: Your Media Hub from the Terminal


# Transforming Photos into Powerful Video Stories

Every photo has a story to tell, but sometimes a single frame isn't enough to capture the full narrative. That's where the magic of video storytelling comes in.

## The Power of Sequential Storytelling

When you arrange photos in sequence, something remarkable happens – you create time, emotion, and connection. A video allows you to:

- **Control pacing** and guide the viewer's emotional journey
- **Add layers** with music, transitions, and effects
- **Create atmosphere** that individual photos can't achieve alone
- **Tell complex stories** across multiple moments

## Planning Your Visual Narrative

### 1. Identify Your Story Arc

Before diving into video creation, ask yourself:
- What emotion do you want to convey?
- What's the beginning, middle, and end?
- Which photos are your "hero shots"?
- How do you want viewers to feel?

### 2. Curate Your Photo Selection

Not every photo needs to make it into your video. Focus on:
- **Emotional peaks** – moments of highest impact
- **Transition moments** – photos that bridge scenes
- **Detail shots** – close-ups that add texture and intimacy
- **Wide establishing shots** – that set the scene

## AI-Powered Video Creation

Modern AI tools can transform your creative process:

### Intelligent Sequencing
AI can analyze your photos for:
- Visual similarity and flow
- Color harmony across frames
- Emotional content and mood
- Optimal sequence ordering

### Automated Enhancements
- **Smart transitions** that match your content style
- **Audio synchronization** with visual beats
- **Color grading** for consistency
- **Pace optimization** based on content analysis

## Creative Techniques for Impact

### 1. The Ken Burns Effect
Add life to static photos with subtle zoom and pan movements. This classic technique:
- Creates visual interest in still images
- Directs attention to important details
- Adds cinematic quality to your narrative

### 2. Rhythm and Pacing
- **Fast cuts** for energy and excitement
- **Slow transitions** for contemplative moments
- **Beat matching** with music for emotional impact
- **Breathing room** – don't rush the story

### 3. Color and Mood
Use color grading to enhance your story:
- **Warm tones** for happiness and comfort
- **Cool tones** for calm or melancholy
- **High contrast** for drama
- **Desaturated** for vintage or serious themes

## Technical Considerations

### Export Settings
- **Resolution**: 1080p minimum, and lower for fast social media uploads
- **Frame rate**: 24fps for cinematic feel, 30fps for smooth motion
- **Compression**: Balance quality with file size
- **Audio**: 48kHz for professional sound quality

### Platform Optimization
Different platforms have different requirements:
- **Instagram**: Square or vertical formats
- **YouTube**: Horizontal 16:9 aspect ratio
- **TikTok**: Vertical 9:16 format
- **Twitter**: Short, punchy content under 2 minutes

## The Emotional Journey

Remember that great video storytelling is about emotion, not just technical perfection:

- **Start strong** – capture attention in the first 3 seconds
- **Build tension** – create anticipation and release
- **Pay off promises** – deliver on what you set up
- **End memorably** – leave viewers with something to think about

## Tools and Workflows

### 5AM's Video Generation
Our AI-powered video creation tools can help you:
- Automatically sequence photos for maximum impact
- Generate professional transitions and effects
- Sync music and audio to visual beats
- Export in multiple formats for different platforms

### Creative Process
1. **Import** your photo album
2. **Select** your narrative style
3. **Customize** pacing and transitions
4. **Preview** and refine
5. **Export** in your preferred format

## Beyond Basic Slideshows

Don't settle for simple photo slideshows. Think about:
- **Mixed media** – combining photos, video clips, and graphics
- **Interactive elements** – for web-based presentations
- **Multiple storylines** – parallel narratives that converge
- **Audience participation** – encouraging engagement and sharing

## The Future of Visual Storytelling

As AI tools continue to evolve, we're moving toward:
- **Personalized narratives** that adapt to viewer preferences
- **Real-time generation** of videos from live photo streams
- **Collaborative storytelling** where audiences contribute content
- **Cross-platform optimization** that automatically adapts content

## Start Your Story Today

The best time to start experimenting with video storytelling is now. Every photo collection has the potential to become something extraordinary.

Your photos are the raw material – now it's time to bring them to life.

**Ready to transform your photos into compelling videos?** [Explore 5AM's Video Generation Tools](/features/video-generation)

Learn how to transform your static photo albums into compelling video narratives using AI-powered tools and creative techniques.

The Art of Visual Storytelling: From Photos to Videos


# AI as Your Creative Partner

Artificial Intelligence isn't here to replace artists; it's here to amplify your creative potential. Let's explore how to make AI your most valuable creative partner, pushing your ideas into uncharted territory.

## Understanding AI's Role in Your Art

AI tools work best when they complement human creativity, not when they try to replace it. Think of AI as:

*   **A creative catalyst** that sparks new ideas and breaks through creative blocks.
*   **An experimental playground** for exploring unexpected styles and visual combinations.
*   **A tireless assistant** that can handle complex or tedious parts of the creation process, freeing you to focus on the vision.
*   **A learning partner** that exposes you to new techniques and aesthetics, helping you grow as an artist.

## Practical AI Techniques for Artists

### 1. Supercharge Ideation and Concept Development

Use AI to brainstorm concepts and explore visual directions you might not have considered on your own. AI can help you:

*   Generate unique mood boards and visual references based on abstract concepts.
*   Explore countless color palettes and compositions in seconds.
*   Create rapid-fire concept sketches to serve as a starting point for your own refinement.

### 2. Enhance Your Technical Execution

Let AI handle some of the technical heavy lifting while you stay in the driver's seat for all creative decisions. You can use it for:

*   Applying intricate styles or textures to your work with style transfer.
*   Simplifying complex tasks like background removal for composite images.
*   Intelligently upscaling and enhancing the quality of your images, allowing for greater detail and clarity.

## Maintaining Your Artistic Voice

The key to using AI effectively is ensuring your unique artistic perspective remains at the core of your work.

*   **Set clear creative intentions** before you begin using any AI tool.
*   **Use AI as a starting point, not an endpoint.** Build upon, modify, and integrate what it generates.
*   **Combine AI outputs** with your traditional techniques, whether digital or physical.
*   **Trust your artistic instincts** above any algorithmic suggestion. You are the artist, the final curator of the piece.

## The Future of AI-Assisted Creativity

As AI tools continue to evolve, the artists who thrive will be those who learn to collaborate with technology. By embracing AI as a partner, you can push the boundaries of your own imagination while maintaining your unique human perspective and creative vision.

AI doesn't make you less of an artist—it makes you a more empowered one.

**Ready to explore AI creative tools?** [Try 5AM's AI features](/features/ai-tools)

Discover how AI can enhance your creative workflow without replacing your artistic vision. Learn practical tips for integrating AI tools into your art practice.

Mastering AI Creative Tools: A Visual Artist's Guide


# Welcome to 5AM Creative Platform

Creativity never sleeps, and neither should your tools. Welcome to 5AM, where your creative journey begins before the world wakes up.

## What Makes 5AM Different?

At 5AM, we believe that the best creative work happens when you have the right tools at your fingertips. Our platform combines cutting-edge AI technology with intuitive design to help you:

- **Store** your creative work securely in the cloud
- **Edit** photos and videos with AI-powered tools
- **Share** your creations with the world
- **Monetize** your artistic vision

## Your First Steps

### 1. Upload Your First Album

Start by creating your first album. Whether it's a photography session, a creative project, or a collection of inspiration, 5AM makes organization effortless.

### 2. Explore AI-Powered Editing

Our AI tools can help enhance your photos, suggest creative edits, and even generate videos from your photo collections. It's like having a creative assistant that never sleeps.

### 3. Share Your Vision

When you're ready, share your work with friends, family, or clients. Set up paid access to monetize your creative efforts, or keep it free for personal sharing.

## Join the 5AM Community

You're not just getting a platform – you're joining a community of creators who understand that inspiration strikes at all hours. Welcome to 5AM, where creativity never sleeps.

Ready to begin? **[Start your creative journey today](/login)**.

A comprehensive guide to unleashing your creative potential with 5AM's powerful tools and features.

Getting Started with 5AM Creative Platform


# From Creative Chaos to Organized Flow

Every artist knows the struggle: brilliant ideas scattered across devices, half-finished projects lost in folders, and that constant feeling that you're not working as efficiently as you could be.

Let's fix that.

## The Foundation: Organize Before You Create

### 1. Establish Your Digital Workspace

Create a consistent structure for all your creative work:

```
Projects/
├── 2024-Winter-Series/
│   ├── RAW/
│   ├── Edited/
│   ├── Finals/
│   └── References/
├── Client-Work/
└── Personal-Projects/
```

### 2. Develop Naming Conventions

Consistent file naming saves hours of searching:
- `2024-01-15_ProjectName_Version01.psd`
- `ClientName_ProjectType_Date_Version.jpg`

## The Creative Process: Structure That Enhances Flow

### Phase 1: Capture and Collect

- **Inspiration gathering**: Save references in organized folders
- **Idea documentation**: Quick sketches and voice notes
- **Resource collection**: Textures, fonts, color palettes

### Phase 2: Plan and Prepare

- **Project briefs**: Even for personal work, write down your goals
- **Mood boards**: Visual direction before you start creating
- **Timeline planning**: Realistic deadlines for each phase

### Phase 3: Create and Iterate

- **Focused work sessions**: Use timers to maintain intensity
- **Regular saves**: Version control prevents lost work
- **Feedback loops**: Share work-in-progress for outside perspective

### Phase 4: Finalize and Archive

- **Final review**: Check against original goals
- **Export optimization**: Right formats for intended use
- **Proper archiving**: Future you will thank present you

## Automation: Let Technology Handle the Routine

### What to Automate
- **File backups**: Set it and forget it
- **Basic photo corrections**: Batch process similar images
- **Social media posting**: Schedule your content
- **Client communications**: Templates for common responses

### What to Keep Manual
- **Creative decisions**: Your artistic vision
- **Client relationships**: Personal touch matters
- **Quality control**: Final approval should always be yours

## Tools That Support Creative Flow

The best tools disappear into your workflow. Look for:

- **Cross-platform sync**: Access your work anywhere
- **Collaboration features**: Easy sharing and feedback
- **Smart organization**: AI-powered tagging and search
- **Export flexibility**: Multiple formats and sizes

## Building Habits That Stick

Start small and build consistently:

1. **End-of-day archiving**: 10 minutes to organize today's work
2. **Weekly reviews**: What worked? What didn't?
3. **Monthly cleanups**: Delete unnecessary files, reorganize
4. **Quarterly planning**: Set goals for the next season

## The Payoff: More Time for What Matters

A good workflow system gives you:
- **Mental clarity**: Know where everything is
- **Creative confidence**: Focus on ideas, not logistics
- **Professional polish**: Consistent, high-quality output
- **Scalable growth**: Systems that grow with your success

Remember: The best workflow is the one you actually use. Start simple, stay consistent, and adjust as you grow.

**Ready to streamline your creative process?** [Explore 5AM's organizational tools](/features/photo-management)

Transform your creative process with smart organization, automated workflows, and strategic planning. Learn how successful artists structure their work.

5AM
Blog

Featured Posts