Skip to main content
Glama

Create talking photo

create_talking_photo

Use only with the user's own likeness or content they are authorized to use. Do not use for impersonation, deception, sexual content, or content involving minors.

Use a still portrait and an existing speech recording to make the portrait speak. A written script needs audio first. For a prepared ad image and written script, use create_spoken_ad_video. For existing video and replacement audio, use create_lip_sync_video. Starts a background job that costs credits; returns a project id for wait_for_video_project. Before choosing settings, read get_account_info and the current parameter constraints. A listed model, resolution, duration or count is not necessarily available together or on this account. Preserve explicit requirements and all supplied inputs; explain a genuine block instead of submitting an incompatible request. Account balance alone does not prove a request is affordable. Use the named attachment fields first for ChatGPT files. Ask which file goes where if their roles are unclear. If a file fails, ask the user to attach it again and keep the requested settings.

Input Schema

NameRequiredDescriptionDefault
nameNoOptional project name for identifying this output. Omit to use the API's default project name.Talking Photo - dateTime
audioNoAttach the audio from ChatGPT for this input.
imageNoAttach the image from ChatGPT for this input.
styleNoAttributes used to dictate the style of the output
assetsNoProvide the assets for creating a talking photo
resolutionNoOutput preset. Overrides `max_resolution`. Defaults to 480p in prompted mode; realistic mode uses the mapped plan maximum.
end_secondsYesThe end time of the input audio in seconds. Maximum clip length depends on style.generation_mode: realistic 300s, prompted 60s.
start_secondsYesThe start time of the input audio in seconds. Maximum clip length depends on style.generation_mode: realistic 300s, prompted 60s.

Output Schema

NameRequiredDescriptionDefault
idYesUnique ID of the video. Use it with the [Get video Project API](https://docs.magichour.ai/api-reference/video-projects/get-video-details) to fetch status and downloads.
credits_chargedYesThe amount of credits deducted from your account to generate the video. If the status is not 'complete', this value is an estimate and may be adjusted upon completion based on the actual FPS of the output video. If video generation fails, credits will be refunded, and this field will be updated to include the refund.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • addedInput schema / allOf
      Added value: +[
      +  {
      +    "anyOf": [
      +      {
      +        "required": [
      +          "image"
      +        ]
      +      },
      +      {
      +        "properties": {
      +          "assets": {
      +            "required": [
      +              "image_file_path"
      +            ]
      +          }
      +        },
      +        "required": [
      +          "assets"
      +        ]
      +      }
      +    ]
      +  },
      +  {
      +    "anyOf": [
      +      {
      +        "required": [
      +          "audio"
      +        ]
      +      },
      +      {
      +        "properties": {
      +          "assets": {
      +            "required": [
      +              "audio_file_path"
      +            ]
      +          }
      +        },
      +        "required": [
      +          "assets"
      +        ]
      +      }
      +    ]
      +  }
      +]
    • removedInput schema / properties / assets / required
      Removed value: -[
      -  "image_file_path",
      -  "audio_file_path"
      -]
    • addedInput schema / properties / audio
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Attach the audio from ChatGPT for this input.",
      +  "properties": {
      +    "download_url": {
      +      "description": "Exact HTTPS download URL supplied for the native ChatGPT attachment, including its signed query.",
      +      "title": "Download Url",
      +      "type": "string"
      +    },
      +    "file_id": {
      +      "description": "Native ChatGPT file identifier paired with download_url; not a local filesystem path.",
      +      "title": "File Id",
      +      "type": "string"
      +    },
      +    "file_name": {
      +      "default": "",
      +      "description": "Original attachment filename, when supplied by ChatGPT.",
      +      "title": "File Name",
      +      "type": "string"
      +    },
      +    "mime_type": {
      +      "default": "",
      +      "description": "Attachment MIME type, when supplied by ChatGPT.",
      +      "title": "Mime Type",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "download_url",
      +    "file_id"
      +  ],
      +  "title": "ChatGPTFile",
      +  "type": "object"
      +}
    • addedInput schema / properties / image
      Added value: +{
      +  "additionalProperties": false,
      +  "description": "Attach the image from ChatGPT for this input.",
      +  "properties": {
      +    "download_url": {
      +      "description": "Exact HTTPS download URL supplied for the native ChatGPT attachment, including its signed query.",
      +      "title": "Download Url",
      +      "type": "string"
      +    },
      +    "file_id": {
      +      "description": "Native ChatGPT file identifier paired with download_url; not a local filesystem path.",
      +      "title": "File Id",
      +      "type": "string"
      +    },
      +    "file_name": {
      +      "default": "",
      +      "description": "Original attachment filename, when supplied by ChatGPT.",
      +      "title": "File Name",
      +      "type": "string"
      +    },
      +    "mime_type": {
      +      "default": "",
      +      "description": "Attachment MIME type, when supplied by ChatGPT.",
      +      "title": "Mime Type",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "download_url",
      +    "file_id"
      +  ],
      +  "title": "ChatGPTFile",
      +  "type": "object"
      +}
    • changedInput schema / required
      Previous value: -[
      -  "start_seconds",
      -  "end_seconds",
      -  "assets"
      -]New value: +[
      +  "start_seconds",
      +  "end_seconds"
      +]
  2. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"Give your video a custom name for easy identification."New value: +"Optional project name for identifying this output. Omit to use the API's default project name."
  3. Added

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, so the safety profile is covered; the description still adds substantive context the annotations cannot: it starts a background job, costs credits, and returns a project id consumed by wait_for_video_project. It also warns that listed model/resolution/duration combinations may not be simultaneously available on the account, which is real behavioral insight. It stops short of describing failure/retry behavior for a submitted job beyond file re-attachment advice.

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

Conciseness4/5

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

Content is dense but each block (policy guardrails, core purpose, sibling routing, job/cost behavior, pre-flight checks, file handling) does work and is mostly front-loaded. The main structural flaw is that the compliance guardrail occupies the first line, ahead of what the tool actually does, and a couple of sentences ('Preserve explicit requirements and all supplied inputs…', 'Account balance alone does not prove a request is affordable') are abstract policy prose rather than actionable tool guidance.

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

Completeness5/5

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

For an 8-parameter, nested, asynchronous, credit-consuming generation tool, the description covers the things that actually determine correct invocation: what inputs must already exist, which sibling to pick instead, the async job model and its consumer, the credit cost, and the need to verify constraints before choosing settings. Return values need no explanation because an output schema exists.

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 already documents every field, including the mode-dependent duration limits and the enum aliases. The description adds only partial extra meaning, mainly 'use the named attachment fields first for ChatGPT files' and 'ask which file goes where if their roles are unclear', which gestures at the anyOf choice between image/audio and assets.*_file_path without resolving it. No added guidance on start_seconds/end_seconds relative to audio length beyond what the schema states.

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 second sentence gives a specific verb+resource+inputs: 'Use a still portrait and an existing speech recording to make the portrait speak.' It then explicitly names what it is not (create_spoken_ad_video for image+script, create_lip_sync_video for video+audio), so an agent can discriminate it from siblings without opening a schema.

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

Usage Guidelines5/5

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

Routing is explicit and conditional: written script → needs audio first; prepared ad image + script → create_spoken_ad_video; existing video + new audio → create_lip_sync_video. It also names a prerequisite tool (get_account_info) and a follow-up tool (wait_for_video_project), plus an inclusion boundary for impersonation/minors/sexual content.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.