Skip to main content
Glama

create_replica

Build an AI replica from a training video to generate synthetic video content with customizable properties like gaze correction and background options.

Instructions

Create a new AI replica from a training video

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
train_video_urlYesDirect link to training video (S3, etc.)
replica_nameNoName for the replica
consent_video_urlNoOptional separate consent video URL
callback_urlNoURL to receive training completion callback
model_nameNoPhoenix model version (phoenix-3 default)
propertiesNoAdditional replica properties

Implementation Reference

  • Handler function that executes the create_replica tool logic - makes a POST request to /replicas endpoint with the provided arguments and returns the response data as formatted JSON text
    private async createReplica(args: any) {
      const response = await this.axiosInstance.post('/replicas', args);
      return {
        content: [{
          type: 'text',
          text: JSON.stringify(response.data, null, 2),
        }],
      };
    }
  • Tool schema definition with name, description, and inputSchema specifying the structure and validation rules for create_replica tool inputs (train_video_url is required, plus optional replica_name, consent_video_url, callback_url, model_name, and properties)
    {
      name: 'create_replica',
      description: 'Create a new AI replica from a training video',
      inputSchema: {
        type: 'object',
        properties: {
          train_video_url: {
            type: 'string',
            description: 'Direct link to training video (S3, etc.)',
          },
          replica_name: {
            type: 'string',
            description: 'Name for the replica',
          },
          consent_video_url: {
            type: 'string',
            description: 'Optional separate consent video URL',
          },
          callback_url: {
            type: 'string',
            description: 'URL to receive training completion callback',
          },
          model_name: {
            type: 'string',
            description: 'Phoenix model version (phoenix-3 default)',
            enum: ['phoenix-2', 'phoenix-3'],
          },
          properties: {
            type: 'object',
            description: 'Additional replica properties',
            properties: {
              gaze_correction: { type: 'boolean' },
              background_green_screen: { type: 'boolean' },
            },
          },
        },
        required: ['train_video_url'],
      },
    },
  • src/index.ts:692-693 (registration)
    Registration/routing logic in CallToolRequestSchema handler that maps the 'create_replica' tool name to its handler method
    case 'create_replica':
      return await this.createReplica(request.params.arguments);
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure but only states the action ('Create') without details on permissions, rate limits, training time, or response format. It misses critical context like whether this is an async operation (implied by callback_url but not explicit) or what happens on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that directly states the tool's purpose with zero waste. It is appropriately sized for the complexity, avoiding unnecessary elaboration while being immediately clear.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with 6 parameters, no annotations, and no output schema, the description is incomplete. It lacks behavioral context (e.g., training process, async nature), does not explain the callback_url's role, and provides no guidance on usage versus siblings, leaving significant gaps for an AI agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all 6 parameters. The description adds no parameter-specific information beyond what's in the schema, such as explaining the relationship between train_video_url and consent_video_url. Baseline 3 is appropriate as the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the specific action ('Create a new AI replica') and resource ('from a training video'), distinguishing it from siblings like 'create_conversation' or 'create_persona' which involve different resources. It precisely communicates the tool's function without ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives like 'create_persona' or 'patch_persona', nor does it mention prerequisites or exclusions. It lacks context for distinguishing among creation tools in the sibling set, leaving usage decisions unclear.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/rakeshdavid/Tavus-MCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server