Skip to main content
Glama
hermoso-ai

Hermoso

Official
by hermoso-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

Generate talking avatar

generate_avatar

Animate a still portrait so it speaks a supplied script with a lip-synced voice. Use for talking-photo requests, not real filmed footage.

Instructions

ANIMATE A PHOTO so it talks: the presenter in image says script word for word, a separate voice lip-synced onto the still. Use it ONLY when the user asks for an animated photo / talking photo / lip-sync look by name; for any other talk-to-camera or spokesperson ask use generate_video with speak (the person filmed saying it, which reads as real footage). About 1-3 min, holds the pose steady, 480p/720p. The per-second credit price is in hermoso_capabilities (avatarEngines); dryRun:true returns this exact job's hold without rendering. Blocks until done where the host allows, else returns a job id to poll with get_job. Requires canAvatar. Spends credits; a refusal before rendering costs nothing.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNofixed seed, only for an engine other than standard
imageYeslocal path or URL of the presenter portrait. Using a real person’s face, likeness or voice confirms you are them or have their consent, take full, unlimited responsibility for its use and will cover any claim against Hermoso (hermoso.ai/terms). Paid plan only; recorded.
voiceNovoice name (Aria / Sarah / George / Adam). Leave it out and the voice matches the person in `image`; if nobody can be read, the call is refused free asking for one
dryRunNoreturn the credits this exact job would hold, without rendering
engineNoleave out for the standard engine; only an engine listed in hermoso_capabilities avatarEngines is accepted
promptNomotion direction, only for an engine other than standard that hermoso_capabilities lists
scriptYesthe words the avatar speaks
resolutionNo'720p' (default) or '480p'
acceptQueueNoonly for an engine hermoso_capabilities marks oneAtATime: wait in line

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed8 schema fields changedv0.1.366
    • addedInput schema / properties / acceptQueue
      Added value: +{
+  "description": "only for an engine hermoso_capabilities marks oneAtATime: wait in line",
+  "type": "boolean"
+}
    • addedInput schema / properties / dryRun
      Added value: +{
+  "description": "return the credits this exact job would hold, without rendering",
+  "type": "boolean"
+}
    • addedInput schema / properties / engine
      Added value: +{
+  "description": "leave out for the standard engine; only an engine listed in hermoso_capabilities avatarEngines is accepted",
+  "type": "string"
+}
    • changedInput schema / properties / image / description
      Previous value: -"local path or URL of the presenter portrait; a real person’s photo confirms their likeness consent"New value: +"local path or URL of the presenter portrait. Using a real person’s face, likeness or voice confirms you are them or have their consent, take full, unlimited responsibility for its use and will cover any claim against Hermoso (hermoso.ai/terms). Paid plan only; recorded."
    • addedInput schema / properties / prompt
      Added value: +{
+  "description": "motion direction, only for an engine other than standard that hermoso_capabilities lists",
+  "type": "string"
+}
    • changedInput schema / properties / resolution / description
      Previous value: -"'1080p' (default) or '480p'/'720p' draft"New value: +"'720p' (default) or '480p'"
    • addedInput schema / properties / seed
      Added value: +{
+  "description": "fixed seed, only for an engine other than standard",
+  "maximum": 9007199254740991,
+  "minimum": -9007199254740991,
+  "type": "integer"
+}
    • changedInput schema / properties / voice / description
      Previous value: -"voice name (Rachel/Sarah/George/Adam)"New value: +"voice name (Aria / Sarah / George / Adam). Leave it out and the voice matches the person in `image`; if nobody can be read, the call is refused free asking for one"
  2. Changed1 schema field changedv0.1.285
    • changedInput schema / properties / image / description
      Previous value: -"local path or URL of the presenter portrait"New value: +"local path or URL of the presenter portrait; a real person’s photo confirms their likeness consent"
  3. Changed2 schema fields changedv0.1.161
    • changedInput schema / properties / resolution / description
      Previous value: -"'720p' (default) or '480p' draft"New value: +"'1080p' (default) or '480p'/'720p' draft"
    • changedOutput schema / (root)
      Previous value: -{
-  "$schema": "http://json-schema.org/draft-07/schema#",
-  "additionalProperties": false,
-  "properties": {
-    "jobId": {
-      "description": "the render job id — poll get_job with this id to resume or inspect",
-      "type": "string"
-    },
-    "model": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "the product-facing label of the model that rendered it"
-    },
-    "raw": {
-      "description": "the raw job result payload (e.g. images[] for carousel template ads)"
-    },
-    "stillRendering": {
-      "description": "true when the render is still in progress — keep polling get_job with jobId",
-      "type": "boolean"
-    },
-    "url": {
-      "anyOf": [
-        {
-          "type": "string"
-        },
-        {
-          "type": "null"
-        }
-      ],
-      "description": "the served URL of the finished media (absent/null while still rendering)"
-    }
-  },
-  "type": "object"
-}New value: +null
  4. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover safety/idempotency flags, but the description adds the traits that actually matter: ~1-3 min runtime, steady pose, 480p/720p output, pricing source (hermoso_capabilities avatarEngines), dryRun returning the exact hold cost, blocking-vs-job-id semantics, the canAvatar requirement, credit spend, and that a pre-render refusal is free.

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?

Front-loaded with the imperative core ('ANIMATE A PHOTO so it talks') and every clause carries load-bearing information. It is a dense run-on paragraph, however, so the pricing, job-polling, and permission details all compete in a single block rather than being separately scannable.

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 a 9-param, no-output-schema, credit-spending generation tool, the description covers everything an agent needs: execution mode (block vs job id + get_job), cost source, permissions, error/free-refusal behavior, and resolution options. Nothing material is left unstated.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3; the description still adds relational meaning the schema doesn't spell out, tying `image`+`script` to the core behavior ('says `script` word for word') and describing dryRun as returning 'this exact job's hold without rendering'. It doesn't document the less-central params like seed, engine, prompt, acceptQueue.

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?

States a specific verb and resource ('ANIMATE A PHOTO so it talks') with the exact mechanism: a still portrait lip-synced to a separate voice. It explicitly contrasts itself with the sibling generate_video and the 'speak' mode, so an agent can distinguish the two without reading either 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?

Gives an explicit gate ('Use it ONLY when the user asks for an animated photo / talking photo / lip-sync look by name') plus the alternative and its condition ('for any other talk-to-camera or spokesperson ask use generate_video with `speak`'). When-to-use, when-not-to-use, and the substitute are all named.

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

Deploy Server

Other Tools