# Program
> AI-powered video composition platform

## Tool Reference

### Composition

#### Add Scene (`addScene`) [CLI, Agent]

Add a new code scene with React/Remotion component code to the composition. All visual scenes are code_scene type.

**Parameters:**
- `title` (unknown, required): 
- `code` (unknown, required): 
- `duration` (unknown, required): 
- `start` (unknown, required): 
- `layer` (unknown, required): 

#### Delete Scene (`deleteScene`) [CLI, Agent]

Delete a specific scene from the composition by its ID

**Parameters:**
- `sceneId` (unknown, required): 

#### Delete All Scenes (`deleteAllScenes`) [CLI, Agent]

Delete ALL scenes from the composition to start fresh

No parameters required.

#### Set Metadata (`setMetadata`) [CLI, Agent]

Update the composition's metadata like title, description, duration, and dimensions

**Parameters:**
- `title` (unknown, required): 
- `description` (unknown, required): 
- `script` (unknown, required): 
- `duration` (unknown, required): 
- `fps` (unknown, required): 
- `width` (unknown, required): 
- `height` (unknown, required): 

#### Update Scene (`updateScene`) [CLI, Agent]

Update an existing scene's code by providing new code directly or AI-powered instructions

**Parameters:**
- `sceneId` (unknown, required): 
- `code` (unknown, required): 
- `updateInstructions` (unknown, required): 
- `title` (unknown, required): 

#### Update Scene Timing (`updateSceneTiming`) [Agent]

Update a scene's duration or start time with automatic adjustment of subsequent scenes

**Parameters:**
- `sceneId` (unknown, required): 
- `duration` (unknown, required): 
- `start` (unknown, required): 
- `adjustSubsequentScenes` (unknown, required): 

### Query

#### Assess Composition (`assessComposition`) [CLI, Agent]

Get a lightweight overview of the composition showing all scenes with their metadata and status (token-efficient)

No parameters required.

#### Read Composition (`readComposition`) [CLI, Agent]

Read the current composition to see its metadata and planned scenes

No parameters required.

### Generation

#### Generate Speech (`generateSpeech`) [CLI, Agent]

Generate speech audio from text and add as audio scene. Requires a model ID - call listSpeechModels first to get available options.

**Parameters:**
- `text` (unknown, required): 
- `model` (unknown, required): 
- `sceneId` (unknown, required): 
- `start` (unknown, required): 
- `duration` (unknown, required): 
- `voice` (unknown, required): 
- `modelInputs` (unknown, required): 

#### Generate Scene Content (`generateSceneContent`) [Agent]

Generate actual content for a scene based on its type and metadata. For code_scene: generates React/Remotion code. Automatically marks scene as 'final' when done.

**Parameters:**
- `sceneId` (unknown, required): 
- `additionalInstructions` (unknown, required): 

#### Generate Video (`generateVideo`) [CLI, Agent]

Generate a video from a text prompt and add as video scene. Requires a model ID - call listVideoModels first to get available options.

**Parameters:**
- `prompt` (unknown, required): 
- `model` (unknown, required): 
- `sceneId` (unknown, required): 
- `start` (unknown, required): 
- `modelInputs` (unknown, required): 

#### Generate Image (`generateImage`) [CLI, Agent]

Generate an image from a text prompt and add as image scene. Requires a model ID - call listImageModels first to get available options.

**Parameters:**
- `prompt` (unknown, required): 
- `model` (unknown, required): 
- `sceneId` (unknown, required): 
- `start` (unknown, required): 
- `duration` (unknown, required): 
- `modelInputs` (unknown, required): 

#### Transcribe Audio (`transcribeAudio`) [CLI, Agent]

Transcribe audio to text with word-level timestamps

**Parameters:**
- `audioUrl` (unknown, required): 
- `model` (unknown, required): 

### Planning

#### Plan Scene (`planScene`) [Agent]

Plan a scene scaffold. For audio_scene scenes, creates a placeholder that generateSpeech will fill in - use description field for the text to speak. Returns sceneId that should be passed to generateSpeech.

**Parameters:**
- `type` (unknown, required): 
- `start` (unknown, required): 
- `duration` (unknown, required): 
- `title` (unknown, required): 
- `description` (unknown, required): 
- `layer` (unknown, required): 
- `visualStyle` (unknown, required): 
- `animationType` (unknown, required): 
- `assets` (unknown, required): 
- `componentName` (unknown, required): 
- `videoQuery` (unknown, required): 
- `audioType` (unknown, required): 

#### Run Template (`runTemplate`) [Agent]

Execute a workflow template. Only available when organization context is provided.

**Parameters:**
- `templateId` (unknown, required): 
- `inputs` (unknown, required): 

### Utility

#### List Speech Models (`listSpeechModels`) [CLI, Agent]

List available text-to-speech models and their voices. Call this before generating speech to see which models and voices are available.

No parameters required.

#### List Video Models (`listVideoModels`) [CLI, Agent]

List available video generation models. Call this before generating video to see which models are available and their capabilities.

No parameters required.

#### List Image Models (`listImageModels`) [CLI, Agent]

List available image generation models. Call this before generating images to see which models are available and their capabilities.

No parameters required.

#### Upload File (`uploadFile`) [CLI, Agent]

Upload a local file payload to Convex storage for use in composition scenes

**Parameters:**
- `fileName` (unknown, required): 
- `mimeType` (unknown, required): 
- `dataBase64` (unknown, required): 
- `category` (unknown, required): 
- `metadata` (unknown, required):