Clipwright

List voices

list_voices

Read-only

Browse and filter available voices by language, gender, age, use case, and model to pick narration for UGC or faceless videos, then preview samples before paying.

Instructions

Voices for voice of make_ugc, or with skill=make_faceless of make_faceless; the other skill refuses a voice before any charge. Filter by language, gender, age, use_case and model; an unknown value is refused with the allowed ones. Play preview_url before a paid render; it expires. Free.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_voices"
  }
}

Input Schema

Name	Required	Description	Default
`age`	No
`model`	No
`skill`	No
`gender`	No
`language`	No
`use_case`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedv0.45.0Nov 7, 2026

removedInput schema / properties / age / description

Removed value: -"Age label as list_voices prints it (young, middle_aged, old); an unknown value is refused with the allowed list"

removedInput schema / properties / gender / description
```
Removed value: -"Gender label of the voice"
```

removedInput schema / properties / language / description

Removed value: -"Native language of the voice. A filter, not a limit: any voice speaks any supported language."

removedInput schema / properties / model / description

Removed value: -"Only voices this speech model speaks: presets and catalog voices whose language it supports, or the model's own voices (kind model_voice)."

removedInput schema / properties / skill / description

Removed value: -"The skill whose voices to list: make_faceless lists the narration voices of make_faceless (kind faceless_voice), make_ugc every other voice."

removedInput schema / properties / use_case / description

Removed value: -"Use case label as list_voices prints it (narrative_story, social_media, …); an unknown value is refused with the allowed list"

Changed4 schema fields changedv0.39.0Nov 3, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

changedInput schema / properties / language / description

Previous value: -"Native language of the voice. A filter, not a limit: any voice speaks any supported language. A voice with no language of its own (kind model_voice) matches the languages measured on its model"New value: +"Native language of the voice. A filter, not a limit: any voice speaks any supported language."

changedInput schema / properties / model / description

Previous value: -"Only voices this speech model speaks: presets and catalog voices whose language it supports, or the model's own voices (kind model_voice). These are the models of make_ugc: no make_faceless voice matches"New value: +"Only voices this speech model speaks: presets and catalog voices whose language it supports, or the model's own voices (kind model_voice)."

changedInput schema / properties / skill / description

Previous value: -"The skill whose voices to list: make_faceless lists the narration voices of make_faceless (kind faceless_voice), make_ugc every other voice. Omitted means make_ugc. A voice is refused by the other skill before any charge"New value: +"The skill whose voices to list: make_faceless lists the narration voices of make_faceless (kind faceless_voice), make_ugc every other voice."

Changed2 schema fields changedv0.27.0Oct 14, 2026

changedInput schema / properties / model / description

Previous value: -"Only voices this speech model speaks: presets and catalog voices whose language it supports, or the model's own voices (kind model_voice)"New value: +"Only voices this speech model speaks: presets and catalog voices whose language it supports, or the model's own voices (kind model_voice). These are the models of make_ugc: no make_faceless voice matches"

addedInput schema / properties / skill

Added value: +{
+  "description": "The skill whose voices to list: make_faceless lists the narration voices of make_faceless (kind faceless_voice), make_ugc every other voice. Omitted means make_ugc. A voice is refused by the other skill before any charge",
+  "enum": [
+    "make_ugc",
+    "make_faceless"
+  ],
+  "type": "string"
+}

Changed3 schema fields changedv0.25.0Oct 4, 2026

changedInput schema / properties / language / description

Previous value: -"Native language of the voice. A filter, not a limit: any voice speaks any supported language"New value: +"Native language of the voice. A filter, not a limit: any voice speaks any supported language. A voice with no language of its own (kind model_voice) matches the languages measured on its model"

changedInput schema / properties / model / description

Previous value: -"Only voices whose language this speech model supports"New value: +"Only voices this speech model speaks: presets and catalog voices whose language it supports, or the model's own voices (kind model_voice)"

changedInput schema / properties / model / enum

Previous value: -[
-  "eleven_v3",
-  "eleven_flash_v2_5",
-  "eleven_turbo_v2_5"
-]New value: +[
+  "eleven_v3",
+  "eleven_flash_v2_5",
+  "eleven_turbo_v2_5",
+  "eleven_v4",
+  "gemini-3.8-flash-tts"
+]

First observedv0.20.0Sep 25, 2026

TDQS

A3.7/5.0

Behavior4/5

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

The annotations already declare a safe read, so the description's job is to add the operational details, and it does: the call is free, unknown filter values are refused with the allowed set, preview URLs expire, and a voice from the wrong skill errors before any charge. What it doesn't disclose is whether results are paginated or how large the catalog is.

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?

It is short with no filler, but the sentence fragments ('Voices for voice of make_ugc', 'Free.') read as compressed notes rather than front-loaded prose, forcing the agent to reconstruct the grammar. Tightening into two well-formed sentences would preserve the same content with less parsing effort.

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

Completeness3/5

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

With six parameters, no schema descriptions and no output schema, the definition should describe the returned shape; it mentions preview_url and its expiry but never says the response carries the voice identifiers/names the agent must feed into make_ugc or make_faceless. That missing handoff detail is the main gap for a tool whose whole purpose is to supply an input to a sibling.

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 0%, so the description must compensate, and it names five of the six filters (language, gender, age, use_case, model) plus skill in prose. However it adds no value syntax for the free-text filters age and use_case, and does not explain the model enum or how filters interact, so several parameters remain semantically opaque.

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 identifies the resource as voice catalogs and ties them to the two consuming skills ('Voices for voice of make_ugc, or with skill=make_faceless of make_faceless'), so an agent can tell it apart from list_actors, list_template_sounds and list_assets. The wording is telegraphic ('Voices for voice of make_ugc') and never states the verb 'list' outright, but the intent remains recoverable.

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

Usage Guidelines4/5

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

It gives clear context: pick the skill whose voice catalog you need via skill, and the other skill will refuse a voice, so a mismatched choice fails rather than silently succeeding. It also advises playing preview_url before committing to a paid render. What it omits is the direct sequencing instruction ('call this before make_ugc/make_faceless to obtain a voice identifier').

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

Deploy Server

List voices

Instructions

Tool call template

Input Schema

Schema Changelog

TDQS

Other Tools