Skip to main content
Glama

nanoodle

by io.github.nanoodlecom
OverviewDiscussionsAdmin

talking-avatar

Create a short spoken introduction with a fictional presenter. Muse makes the portrait, MiniMax Speech reads the script, and LongCat combines the image and audio into a speaking video at 480p. Keep… text:Presenter look -> text:Spoken script -> text:Delivery -> image:face -> tts -> lipsync; returns video (longcat-avatar-1.5) saved to disk (file path in result). Runs on NanoGPT — $0.66 deposit per call, paid in Nano (XNO) — settles at actual model cost + 20%, change returned; no account needed. Example: Video sample (https://nanoodle.com/examples/gallery/#talking-avatar). A fictional presenter reads a short workshop introduction. Sampled frames preserve the presenter; check precise lip-sync timing in playback. Generation can take several minutes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
DeliveryNoText; default: "Natural calm delivery, subtle blinks and small head movements. Keep the face and mouth visible, eyes toward the camer..."; optional
_payment_idNoPayment id from this tool's previous payment-required response. Phase 3 only: after /x402/watch closes with status paid, call again with the same arguments plus this id to open the RESULTS stream. Do not pass it while payment is still pending — monitor the watch SSE first.
Spoken_scriptNoText; default: "Welcome to the workshop. Start with the blue tray on your table. Inside you will find paper, a pencil, and the parts ..."; optional
Presenter_lookNoText; default: "A fictional friendly male museum guide in his thirties, wearing a plain navy shirt, shoulders-up front-facing portrai..."; optional

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / properties / Delivery
      Added value: +{
+  "description": "Text; default: \"Natural calm delivery, subtle blinks and small head movements. Keep the face and mouth visible, eyes toward the camer...\"; optional",
+  "type": "string"
+}
    • addedInput schema / properties / Presenter_look
      Added value: +{
+  "description": "Text; default: \"A fictional friendly male museum guide in his thirties, wearing a plain navy shirt, shoulders-up front-facing portrai...\"; optional",
+  "type": "string"
+}
    • addedInput schema / properties / Spoken_script
      Added value: +{
+  "description": "Text; default: \"Welcome to the workshop. Start with the blue tray on your table. Inside you will find paper, a pencil, and the parts ...\"; optional",
+  "type": "string"
+}
    • removedInput schema / properties / look
      Removed value: -{
-  "description": "Text; default: \"cinematic film still of a night courier, late 20s, on the cliff-walk at Hongyadong, Chongqing, 2:11am: cropped black ...\"; optional",
-  "type": "string"
-}
    • removedInput schema / properties / movement
      Removed value: -{
-  "description": "Text; default: \"Natural talking-head: small nods timed to the speech, Hongyadong lantern-light catching the visor, slight jaw set, st...\"; optional",
-  "type": "string"
-}
    • removedInput schema / properties / speak
      Removed value: -{
-  "description": "Text; default: \"Last drop of the night. Hongyadong, cliff side. If the stairs flood, tell dispatch I climbed it — the package is alre...\"; optional",
-  "type": "string"
-}
  2. Changed5 schema fields changed
    • removedInput schema / properties / Image
      Removed value: -{
-  "description": "* required; image — file path or https URL",
-  "type": "string"
-}
    • addedInput schema / properties / look
      Added value: +{
+  "description": "Text; default: \"cinematic film still of a night courier, late 20s, on the cliff-walk at Hongyadong, Chongqing, 2:11am: cropped black ...\"; optional",
+  "type": "string"
+}
    • changedInput schema / properties / movement / description
      Previous value: -"Text; default: \"exaggerated head movement\"; optional"New value: +"Text; default: \"Natural talking-head: small nods timed to the speech, Hongyadong lantern-light catching the visor, slight jaw set, st...\"; optional"
    • changedInput schema / properties / speak / description
      Previous value: -"Text; default: \"Hi there! I used to be a still photo — then somebody wired three nodes together, and now I won't stop talking.\"; optional"New value: +"Text; default: \"Last drop of the night. Hongyadong, cliff side. If the stairs flood, tell dispatch I climbed it — the package is alre...\"; optional"
    • removedInput schema / required
      Removed value: -[
-  "Image"
-]
  3. First observed

TDQS

B3.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the multi-model pipeline, the return format (video 'longcat-avatar-1.5' saved to disk with a file path in result), the payment model ($0.66 Nano deposit settling at actual cost +20% with change returned), the no-account requirement, and that generation can take several minutes. The only gaps are interaction specifics like streaming/monitoring behavior and failure handling.

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

Conciseness3/5

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

The purpose is front-loaded, but the body is dense and unevenly ordered, mixing pipeline mechanics, pricing, and caveats, with a visibly truncated fragment ('Keep…'). Several sentences carry useful detail, yet the pricing and example notes could be tightened.

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

Completeness4/5

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

For a paid, multi-stage generation tool with no annotations and no output schema, the description is largely complete: it covers what is produced, where it is saved, cost/payment mechanics, expected latency, and a sample link. Minor omissions (concurrency, retries, resolution/frame caveats beyond '480p') remain.

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 all four parameters, including _payment_id's two-phase flow. The description adds only marginal value via the input-flow line ('text:Presenter look -> text:Spoken script -> text:Delivery -> ...'), which hints at stage ordering but no new syntax or semantics beyond the schema.

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

Purpose4/5

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

The description states a specific verb and resource: 'Create a short spoken introduction with a fictional presenter,' and details the pipeline (Muse portrait, MiniMax Speech, LongCat combine) and the artifact returned. It is clearly a talking-avatar video generator, distinct from siblings like sing or photo-to-video, though it never explicitly names or contrasts those siblings.

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?

There is an example use case (a fictional presenter reading a short workshop introduction) but no explicit guidance on when to choose this tool over alternatives such as photo-to-video or sing, nor any stated exclusions. Usage must be inferred from the example and pipeline description.

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

All nanoodle toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources