Skip to main content
Glama

synthesize

Converts text into spoken WAV files with selectable provider and voice, then returns the absolute file path and metadata for use in games, videos, or agent projects.

Instructions

Synthesize speech to a WAV file and return its absolute path plus metadata.

Args: text: Spoken line to generate. provider: piper | pocket | woof | cartesia (default from env / first healthy local). voice: Provider-specific voice id or name (Pocket also accepts an audio prompt URL). filename_hint: Optional short label included in the output filename.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "synthesize"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
voiceNo
providerNo
filename_hintNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior3/5

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

With no annotations, the description carries the whole behavioral burden and does disclose the key side effect (a WAV file is written) plus the provider auto-selection/failover logic. It is silent on overwrite behavior when filename_hint collides, on whether remote providers like cartesia require credentials, and on latency or failure behavior when no provider is healthy.

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?

Front-loaded: purpose and return value come first, then a compact Args block where every line adds parameter detail. Slightly list-like rather than prose, but no sentence is wasted.

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?

An output schema exists, so return values need not be spelled out, and the description still summarizes them. For a four-parameter synthesis tool with no annotations, the remaining gaps (credential needs for remote providers, filename collision behavior, failure modes) are meaningful but not blocking for correct invocation.

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% and the schema has no enum, yet the Args block gives all four parameters meaning: the provider allowed-values list, the env/local fallback default, provider-specific voice id semantics including the Pocket audio-prompt URL case, and what filename_hint actually affects. This is genuine added information an agent cannot get from the schema.

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 opening sentence names a specific verb and resource ('Synthesize speech to a WAV file') and even states the return shape ('absolute path plus metadata'). That is enough for an agent to separate it from the discovery siblings (list_providers, list_voices, provider_status) without opening any schema.

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

Usage Guidelines3/5

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

Usage is only implied: the tool is clearly the generation step, and the provider parenthetical explains default resolution ('default from env / first healthy local'). There is no explicit instruction to call list_providers or list_voices first to obtain a valid voice id, and no stated conditions for choosing one provider over another.

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

Deploy Server

Other Tools