Audexum

Generate speech

generate_speech

Turn text into natural speech and return a link to an MP3 file.

Args:
    text: What to say. Up to 5,000 characters per call (v1: 15,000); split longer text at sentence
        boundaries. On v4 you may put acting tags inline: <laugh> <sigh> <whispers> <short pause> …
    engine: "v4" = most natural (Creator plan and above), "v3" = natural named voices,
        "v2" = 31 languages, "v1" = cheapest. Omit for a good default.
    voice: Voice id from list_voices (e.g. "Kore" on v4, "Atlas" on v3, "F1" on v2). A v4 voice
        name selects v4 by itself.
    language: ISO 639-1 code of the text, e.g. "en", "de", "bg". Default "en".
    style: Optional delivery direction in plain words, e.g. "warm and slow" (v4 and v3).
    speed: 0.5–2.0. Omit for the voice's natural pace.

Spends the user's Audexum credits (characters × the engine's multiplier).

Input Schema

Name	Required	Default
`text`	Yes
`speed`	No
`style`	No
`voice`	No
`engine`	No
`language`	No	en

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 18, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already establish safety hints, and the description adds important behavioral context: credits are spent based on characters times engine multiplier, character limits vary by engine, and v4 supports inline acting tags. It also notes plan restrictions for v4.

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

Conciseness5/5

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

The description is front-loaded with purpose and return value, then uses a compact Args list to document each parameter. Despite its length, every part provides necessary information for a six-parameter tool with no schema descriptions.

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 the complexity, zero schema description coverage, and existing output schema, the description is complete enough to call the tool correctly. It covers inputs, limits, engine tradeoffs, voice sourcing, and credit consumption.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden. It explains every parameter: text limits and tags, engine tiers and defaults, voice ID source and examples, language ISO code and default, style supported engines, and speed range.

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 first sentence states a specific verb and resource: turn text into natural speech and return an MP3 link. It clearly distinguishes this from sibling tools like transcribe and references list_voices for voice selection.

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 strong practical guidance on engine selection, voice IDs, text splitting, and defaults. It does not explicitly state when not to use the tool or name an alternative speech tool, but the usage context is clear.

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

All Audexum tools Inspect

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

Need Help?