Models
The roster is live, resolved from the registry. It is exposed as themodelId enum on each generate tool (MCP), or via contenthero model list (CLI). There is no static model list to memorize; ask the surface.
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 |
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.
Cost preflight
Preview any spend for free withgetCost: true (MCP) or --cost (CLI). The preflight 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 withlist_avatars and the board media reads, and pass them as typed references. The pipeline and the contenthero-generate skill cover the full reference model.