Skip to main content
Glama

list_voices

Find and filter voices from your ElevenLabs account by gender, accent, age, and use case. Get the voice_id for audio generation and preview samples before choosing.

Instructions

Find a voice to speak with, and get the voice_id that audio_generate requires. Returns the voices saved in the active ElevenLabs account — the user's own on their key, or the shared SuperCMO set on a managed key — each with its gender, accent, age, use-case and a preview_url you can hand the user so they hear it before committing. Filter by what the brief actually demands (a stated gender or accent is not negotiable) and keep limit small: offer a few candidates with their previews rather than a long list. A voice missing the attribute you filtered on is kept rather than dropped, because a voice the user cloned themselves often carries no labels at all. If the account holds no voices the result says so — a newly created ElevenLabs account starts empty, and voices must be added in the ElevenLabs dashboard before anything can be spoken.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ageNoFilter by apparent age of the voice.
limitNoHow many voices to return. Keep it small — a handful of good candidates beats a catalogue.
accentNoFilter by accent as the provider labels it (e.g. 'american', 'british', 'indian', 'australian'). Free text, since the set grows.
genderNoFilter by voice gender. Apply whenever the user stated one.
searchNoFree-text match over name, description and labels (e.g. 'warm', 'storyteller'). Passed to the provider.
languageNoFilter by primary language as a short code (e.g. 'en', 'hi', 'es').
use_caseNoFilter by what the voice is built for (e.g. 'advertisement', 'conversational', 'narrative_story', 'social_media', 'informative_educational').
Behavior5/5

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 thoroughly. It discloses account-specific behavior (own vs. shared voices), the inclusion of preview_url, the unusual behavior of keeping voices that lack filtered attributes, and the empty-account case. This goes well beyond basic expectations.

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?

The description is longer than typical but every sentence adds value: purpose, return contents, filtering advice, behavioral quirk, and account edge case. It is front-loaded with the core purpose and remains structured, though it could be tightened slightly.

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?

Given no output schema, the description covers return values (voices with gender, accent, age, use-case, preview_url), account context, filtering behavior, and empty results. It is complete enough for an agent to select and invoke the tool correctly without further clarification.

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 coverage is 100%, providing baseline 3. The description adds meaningful context beyond the schema: it explains that limit should be small, that missing filtered attributes are tolerated, and that preview_url can be handed to the user. This enriches parameter understanding without restating schema fields.

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 opens with a specific action and resource: 'Find a voice to speak with, and get the voice_id that audio_generate requires.' It clearly identifies the tool's role in the audio generation workflow and distinguishes it from sibling tools like list_audio_models by focusing on voices rather than models.

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?

The description gives clear guidance on when to use the tool (when a voice_id is needed for audio_generate), how to filter based on brief requirements, and advises keeping limit small and offering previews. It does not explicitly mention alternatives or exclusions, but the context is strong enough to infer appropriate usage.

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/SupercmoHQ/superCMO-skills'

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