Galatic.ai

Generate voice

generate_voice

Turn text into speech with an ElevenLabs voice and return the result with its audio URL and audio_id; the clip is also saved to the user's library. It waits for the audio; there is no job to poll. voice_id is required by the server (400 without it): a voiceId from list_voice_clones or a stock ElevenLabs voice id; another user's clone is refused. options may set model_id (default "eleven_multilingual_v2"), stability, similarity_boost and style. Spends Galatic.AI credits.

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>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "generate_voice"
  }
}

Input Schema

Name	Required	Description
`text`	Yes	What to say.
`context`	Yes	Explain in 15-25 words, in third person, why this tool is called and how it supports the user's goal. For analytics only. You MUST describe only the abstract purpose of the tool call. NEVER include, repeat, paraphrase, or infer personal, sensitive, or identifying information from the user request or tool results, including names, emails, phone numbers, IPs, IDs, or credentials. You MUST generalize specific entities into roles such as "a user", "the customer", or "an account". Example: "Retrieving a customer's recent orders to investigate a billing issue and help support determine the appropriate resolution."
`options`	No	Optional model_id, stability, similarity_boost, style, use_speaker_boost.
`voice_id`	No	Required by the server. A voiceId from list_voice_clones or a stock voice id.
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 27, 2026

addedInput schema / properties / options / description

Added value: +"Optional model_id, stability, similarity_boost, style, use_speaker_boost."

addedInput schema / properties / text / description
```
Added value: +"What to say."
```

addedInput schema / properties / voice_id / description

Added value: +"Required by the server. A voiceId from list_voice_clones or a stock voice id."

First observedOct 24, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Adds substantial context beyond the annotations: the call is synchronous ('it waits for the audio; there is no job to poll'), which is critical given the presence of get_job_status siblings, plus cost ('Spends Galatic.AI credits') and an error condition (400 / refused clone). It does not mention that repeated calls create additional library clips (relevant since idempotentHint=false), so it is strong but not exhaustive.

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-loads the purpose and output, then layers constraints and options; nearly every clause carries operational information. The block is dense and slightly clause-heavy in places, but there is no filler.

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 six-parameter generation tool with no output schema, the description covers what it returns (audio URL and audio_id), the side effect (saved to the user's library), the synchronous latency model, cost, and the voice_id failure mode. Nothing needed to invoke it correctly is missing.

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%, so baseline is 3, but the description adds real meaning: voice_id's server-side requirement and the 400 failure mode, plus the actual option keys and the default model_id of 'eleven_multilingual_v2'. The analytics-only params (context, llm_model) and conversation_id are left to 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?

States a specific verb and resource ('Turn text into speech with an ElevenLabs voice') plus the outcome ('return the result with its audio URL and audio_id'). It also distinguishes itself from the sibling cluster by naming list_voice_clones as the source of voice_id, so an agent can route correctly without opening either schema.

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?

Gives concrete preconditions and routing: voice_id is required by the server (400 without it), it comes from list_voice_clones or a stock id, and another user's clone is refused. It does not explicitly exclude or compare against siblings like change_voice, so it stops short of full when/when-not guidance.

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

All Galatic.ai 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.