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

# Creating a video

> A full walkthrough of turning a prompt into a finished video.

<Frame>
  <img src="https://mintcdn.com/velo/ges-rbAcLDEpYx4O/images/prompt-to-video/creating-a-video/01.png?fit=max&auto=format&n=ges-rbAcLDEpYx4O&q=85&s=e9a08fa6ce449cd8818c5332f887dcc8" alt="Live preview in the chat, with Render and share this video" width="1468" height="837" data-path="images/prompt-to-video/creating-a-video/01.png" />
</Frame>

Velo builds a **live preview** in the panel as it works. The hint under it reads *"Live preview — ask for changes, or render when you're happy"* — so you can keep adjusting by message before committing to a render.

<Steps>
  <Step title="Start a new chat">
    From your workspace, select **New chat → Prompt**. You'll land in a conversation with the Prompt to Video agent.
  </Step>

  <Step title="Describe the video">
    Type what you want the video to explain — for example, "Explain our new pricing tiers to existing customers" or "Walk a new hire through how our onboarding flow works." Be as specific as you'd be briefing a teammate.
  </Step>

  <Step title="Attach connectors (optional)">
    If you want the script grounded in real product or company context, attach a [knowledge base, MCP server, or application](/prompt-to-video/connectors/overview). This step is optional — the agent can also work from your prompt alone.
  </Step>

  <Step title="Review the script">
    The agent researches your topic and returns a script. Read it over, and ask for changes directly in the conversation — for example, "make this shorter" or "add a section on refunds."
  </Step>

  <Step title="Choose a voice">
    Select a public voice or your own cloned voice (see [Voice clone](/velotwin/voice-clone)) for the voiceover.
  </Step>

  <Step title="Render">
    Once you approve the script and voice, the agent renders the video. It appears in **My Videos** like any other videos — ready to share, edit further, or track.
  </Step>
</Steps>

## After it's rendered

A Prompt to Video video behaves like any other video in your workspace: it can be shared with a link, embedded, translated into other languages (see [Multilingual output](/editing-velo/translations)), and tracked with the same [view analytics](/creating-a-velo/video-analytics). You can also continue editing it by prompt — see [Editing in Prompt to Video](/prompt-to-video/editing).

## Rendering and sharing

When the preview is right, select **Render & share this video**. Velo offers an **Add background music** step, which you can take or **Skip**.

<Frame>
  <img src="https://mintcdn.com/velo/ges-rbAcLDEpYx4O/images/prompt-to-video/creating-a-video/02.png?fit=max&auto=format&n=ges-rbAcLDEpYx4O&q=85&s=4ac6d42fdebd17121cb7b3e499a3f109" alt="Rendered video with Download and Copy link" width="1470" height="776" data-path="images/prompt-to-video/creating-a-video/02.png" />
</Frame>

The finished video appears with **Download** and **Copy link** beneath it. From there it behaves like any other video — see [Sharing](/creating-a-velo/sharing) and [Video analytics](/creating-a-velo/video-analytics).