> ## Documentation Index
> Fetch the complete documentation index at: https://docs.unpod.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Publish & share

> A saved playbook is private to you. Publishing sets its visibility, hands out a share link, lets others clone it, and unlocks two ways to deploy - as a live voice agent on a number, or as a callable API endpoint.

## Save vs. publish

**Saving** (from [Build an agent playbook](/playbook/build-an-agent)) keeps a playbook
private to you as a draft. **Publishing** is the deliberate step that makes it
available to others and unlocks deployment - either **as a voice agent on a phone
number** or **as an API endpoint**. Until you publish, the top bar shows
`Draft — not yet published`.

<Note>
  This page starts after you have a working, saved playbook. If you have not saved
  yet - or want to move a playbook in or out as a file - see
  [Save, import & export](/playbook/build-an-agent#step-4-save-import-export) on the Build page.
</Note>

<Warning>
  Publishing changes who can see and run your agent. Read the visibility levels
  below before you publish - "Public" lists the agent in a gallery anyone can find.
</Warning>

## Step 1 - Publish and set visibility

Hit **Publish** in the top bar. You pick one of three visibility levels, shown by
a badge on the playbook:

| Visibility   | Who can reach it                                                        |
| ------------ | ----------------------------------------------------------------------- |
| **Private**  | Only you.                                                               |
| **Unlisted** | Anyone with the link can open and test it - not discoverable otherwise. |
| **Public**   | Listed in the public gallery for anyone to find and test.               |

You can change visibility at any time; the badge updates and the setting is
saved server-side.

## Step 2 - Share by link

For an **Unlisted** or **Public** playbook, open **Share** to copy a link. Anyone
who opens it lands in the Playground with your agent loaded and can talk to it -
no account needed for the trial.

<Card title="Rotate a leaked link" icon="rotate-ccw">
  If a link gets out, use **Regenerate** in the Share dialog to revoke the old
  link and issue a new one. Old links stop working immediately.
</Card>

<Note>
  Shared access is **view + run**, cross-tenant and project-scoped. Someone opening
  your link can test the agent and clone it; they cannot edit your original.
</Note>

## Step 3 - Let others build on it (clone)

Anyone viewing a shared or public playbook can **Clone & edit** to get their own
private copy. It is the fastest way to hand a teammate a working starting point -
they clone, tweak, and publish their own version without touching yours.

## Step 4 - Deploy

Publishing opens the **deploy drawer**, which offers **two ways to ship** the
same agent. Pick the one that matches how callers will reach it:

<CardGroup cols={2}>
  <Card title="Deploy as Voice Agent" icon="phone">
    Put it on a **real phone number**. Choose a number and the drawer wires up a
    speech pipe for you - inbound callers reach the agent immediately.
  </Card>

  <Card title="Deploy as Endpoint" icon="code">
    Turn it into a **callable API** with an API key, so your own backend drives
    the agent. No phone number involved.
  </Card>
</CardGroup>

Both run the **same published playbook and the same `AgentRunner`** you tested in
Preview - nothing is re-implemented on the way to production.

### Deploy as Voice Agent

<Frame caption="Deploy as Voice Agent - pick a number from the picker, then deploy">
  <img src="https://mintcdn.com/unpodai/djZvOeKNVOnMwvUj/images/playbook/publish-voice-agent.png?fit=max&auto=format&n=djZvOeKNVOnMwvUj&q=85&s=04002e8dbe5ed90882d9ec1bb10b5ee1" alt="Publish drawer on the Deploy as Voice Agent tab, showing a Phone Number picker with a number card and a rotate control, plus Cancel and Deploy as Voice Agent buttons." width="1919" height="960" data-path="images/playbook/publish-voice-agent.png" />
</Frame>

<Steps>
  <Step title="Pick a number">
    The drawer loads your available numbers in a picker - use the rotate control
    to cycle through them. Select one (or choose **No number** to deploy without
    assigning one yet).
  </Step>

  <Step title="Confirm">
    On deploy the platform assigns the number and provisions a **speech pipe**
    behind it - you get a "Deployed!" confirmation with the wired pipe.
  </Step>

  <Step title="Call it">
    Dial the number, or dispatch an outbound call to it. The agent answers with
    the playbook you tested.
  </Step>
</Steps>

<Note>
  Need a number first, or want to manage pipes by hand? See
  [Numbers](/speech-stack/numbers) and [Speech Pipes](/speech-stack/pipes) - the
  Voice Agent deploy is the one-click version of that wiring.
</Note>

### Deploy as Endpoint

Turns the agent into an **OpenAI-compatible** `chat/completions` API. The drawer
shows your **endpoint**, the **model** (your playbook id), and a ready-to-run
snippet in cURL, Python, JavaScript, and Go.

<Frame caption="Deploy as Endpoint - endpoint, model id, Manage API Keys, and per-language snippets">
  <img src="https://mintcdn.com/unpodai/djZvOeKNVOnMwvUj/images/playbook/publish-endpoint.png?fit=max&auto=format&n=djZvOeKNVOnMwvUj&q=85&s=4a8b169216e5fd56f7521e9482a88bfa" alt="Publish drawer on the Deploy as Endpoint tab, showing the inference.unpod.ai endpoint, a public: model id, Manage API Keys, and cURL / Python / JavaScript / Go code tabs." width="1919" height="960" data-path="images/playbook/publish-endpoint.png" />
</Frame>

<Steps>
  <Step title="Deploy & create a key">
    Hit **Deploy as Endpoint**, then **Manage API Keys** to mint one. Copy it now -
    treat it like a password. Rotate it any time if it leaks.
  </Step>

  <Step title="Copy the snippet">
    Pick your language tab. Each snippet is pre-filled with your endpoint, your
    `model` id, and the `Authorization: Bearer $UNPOD_API_KEY` header.
  </Step>

  <Step title="Call it from your app">
    Point any OpenAI SDK at the base URL. The agent runs the exact playbook you
    tested in Preview.
  </Step>
</Steps>

```bash Example theme={null}
curl https://inference.unpod.ai/v1/chat/completions \
  -H "Authorization: Bearer $UNPOD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"public:PB_7ZRMzCA1ojQ9LlcK","messages":[{"role":"user","content":"hi"}]}'
```

<Warning>
  API keys carry your account's access. Store them in a secret manager or
  environment variable (`UNPOD_API_KEY`), never in client-side code or a committed
  file. Revoke and regenerate immediately if one is exposed.
</Warning>

<Card title="Full Endpoint API reference" icon="terminal" href="/playbook/api">
  Stateful sessions (`x_session_id` / `user`), the "empty messages = agent greets
  first" rule, and full Python / JS / Go examples.
</Card>

## Bring your own key (BYOK)

If you want calls billed to **your** provider account instead of the Playground
wallet, open the **BYOK** panel and paste keys for your LLM and speech providers
(OpenAI, Deepgram, Cartesia, ElevenLabs, ...). When set, the Playground routes
through your keys; **Clear** reverts to the shared wallet.

<Note>
  Guest and trial usage draws on a metered wallet - you will see a balance chip and
  an "out of minutes" prompt when it runs low. BYOK sidesteps that by using your
  own provider quota.
</Note>

## Drive the agent from your own code

<Card title="Endpoint API" icon="terminal" href="/playbook/api">
  Once deployed as an endpoint, call the agent over the OpenAI-compatible API -
  stateful sessions, greet-first, and Python / JS / Go examples.
</Card>