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

# Generate

> Image, video, audio, reference boards, and lip-sync, with output-id chaining and cost preflight.

The generate tools turn an idea into media: you bring the prompt, ContentHero produces the asset. Drafting the prompt in the user's voice is the [pipeline](/guides/pipeline)'s job, not this one.

## Models

The roster is live, resolved from the registry. It is exposed as the `modelId` enum on each generate tool (MCP), or via `contenthero model list` (CLI). There is no static model list to memorize; ask for the current one.

## Core operations

| What            | MCP tool            | CLI                             |
| --------------- | ------------------- | ------------------------------- |
| Image           | `generate_image`    | `contenthero generate image`    |
| Video           | `generate_video`    | `contenthero generate video`    |
| Audio (TTS)     | `generate_audio`    | `contenthero generate audio`    |
| Reference board | `generate_board`    | `contenthero generate board`    |
| Lip-sync        | `generate_lip_sync` | `contenthero generate lip-sync` |
| Upscale         | `upscale`           | `contenthero upscale`           |
| Transcribe      | `transcribe`        | `contenthero transcribe`        |

Reads: `list_media` / `get_media` (spanning creations, boards, and looks via the `kind` filter), `list_avatars` / `get_avatar`, `list_voices` / `get_voice`.

## Async

`generate_*` runs a smart-wait of about 50s, then returns the finished asset or an `outputId` if the render is still going. Poll a snapshot with `get_generation_status`, or block with `wait_for_generation` (CLI `contenthero generation wait <id>`). The `outputId` is always returned, so you can always keep polling.

## Chaining outputs

A reference input (start frame, image input, audio for lip-sync) accepts a raw URL **or** a ContentHero output-id token `<uuid>-<N>`, the Nth variation of a prior output. The server resolves either, type-checks it, and scopes it to the owner.

The common chain: generate a key frame, then feed its output id straight into a video as the start frame.

<Steps>
  <Step title="Generate the image">
    `generate_image` with your prompt and `modelId`. Capture the returned output id.
  </Step>

  <Step title="Feed it into video">
    `generate_video` with the image's output-id token as the start frame. No re-upload needed.
  </Step>
</Steps>

## Cost preflight

Preview any cost for free with `getCost: true` (MCP) or `--cost` (CLI). The preview takes the same parameters as the real call, so the quote matches the charge.

## Identity and references

For consistent characters across generations, ContentHero supports avatars and reference boards as reusable identity. Browse them with `list_avatars` and the board media reads, and pass them as typed references. The [pipeline](/guides/pipeline) and the `contenthero-generate` skill cover the full reference model.