Media Generator — Images, Videos & Audios

text_to_speech

Input: Text to convert to speech, language ID, and voice type.

Output: Returns the URL of the generated audio file.

Functionality: This tool converts text to speech in the specified language and voice. It follows these steps:

Gets user_id from context and validates tokens.
Generates speech from the text using the specified language and voice.

Args: text: The text to convert to speech language_id: The language ID (defaults to "en" for English) voice_id: The voice type (defaults to "female")

Returns: The URL of the generated audio file

INSTRUCTION FOR CLIENT MODEL:

Extract the required input parameter 'text' (type: string) and optional parameters 'language_id' (type: string, default 'en') and 'voice_id' (type: string, default 'female') from the user's prompt.
If 'language_id' or 'voice_id' are not specified, use the default values.
Ignore any extraneous information in the user's input.
Pass the extracted values to this tool as 'text', 'language_id', and 'voice_id'.
RECOMMENDATION: Call get_languages() first to see available language IDs before choosing a language_id.
Example: For user input "Convert 'Hello world' to French with a male voice", extract 'text' as 'Hello world', 'language_id' as 'fr', and 'voice_id' as 'male'.

Input Schema

TableJSON Schema

Name	Required	Default
`text`	Yes
`voice_id`	No	female
`language_id`	No	en

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

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

With no annotations, the description discloses internal steps: token validation via user_id, speech generation, and returning a URL. It also mentions defaults and provides an example, adding behavioral context beyond the schema. Missing rate limits or failure modes, but strong for a simple tool.

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 well-structured with headers and front-loaded input/output, but the 'INSTRUCTION FOR CLIENT MODEL' section makes it lengthy. All content is relevant, though it could be trimmed without losing critical information.

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 tool with 3 parameters and no annotations, this description thoroughly covers purpose, usage, parameters, return value, and a companion tool recommendation. The only minor gap is error handling, but the provided info is sufficient for a TTS call.

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 coverage is 0%, so the description fully compensates by documenting all three parameters with types and defaults. It includes an example of extracting values from natural language, which is essential for correct invocation.

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 clearly states it 'converts text to speech in the specified language and voice' and defines the input/output format. It uses a specific verb and resource, making its purpose unambiguous and distinct from sibling tools like image generation.

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 explicitly recommends calling get_languages() first to validate language IDs, providing an alternative/companion tool. It also gives extraction instructions and defaults, but does not state explicit when-not-to-use scenarios, so it falls just short of full guidance.

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

All Media Generator — Images, Videos & Audios tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

Most tools have clearly distinct purposes, such as generate_image, remove_background, and upscale_image. However, logo_generator and generate_image both accept a text prompt and return an image URL, which could cause confusion, and music_generator and song_generator overlap in audio generation, though their inputs differ.

Naming Consistency3/5

Tool names are a mix of verb_noun (generate_image, remove_background), noun_generator (logo_generator, song_generator), and simple verbs (fetch, search, health). While readable, the lack of a single consistent pattern makes it less predictable for an agent.

Tool Count4/5

With 17 tools, the server is slightly above the ideal 3-15 range but not excessively over. Each tool serves a distinct function for generating or manipulating media, so the count feels justified for the broad scope.

Completeness4/5

The toolset covers the core media generation lifecycle: image generation, editing, background removal, upscaling, video generation, image-to-video, music and song generation, and text-to-speech. Minor gaps like video editing or managing past generations exist, but they are not critical for standard workflows.

Resources

Need Help?