Skip to main content
Glama

tts

by com.brainiall

Synthesize Speech

synthesize_speech
Read-onlyIdempotent

Convert text to natural-sounding speech.

Returns WAV audio (16-bit PCM, 24 kHz mono) synthesized with neural voices. 54 voices across 9 languages -- including 3 native Brazilian Portuguese voices (pf_dora, pm_alex, pm_santa). Usage is metered per character.

Args: text: Text to convert to speech (max 5000 characters per request). language: Language code; selects the default voice when no voice is given. voice: Explicit voice ID (see list_voices). Overrides language. speed: Speech speed multiplier, 0.5-2.0. output_format: 'audio' for playable MCP audio content, 'base64_json' for a JSON object with the base64-encoded WAV and metadata.

Returns: MCP audio content (audio/wav), or when output_format='base64_json' a dict with keys: - audio_base64 (str): Base64-encoded WAV bytes - mime_type (str): 'audio/wav' - voice (str): Voice used - characters (int): Characters billed - estimated_cost_usd (float): Estimated cost of this request

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYesText to convert to speech (1-5000 characters per request)
speedNoSpeech speed multiplier (0.5 = half speed, 2.0 = double speed)
voiceNoVoice ID (e.g. 'pf_dora', 'pm_alex', 'af_heart', 'bm_george'). Overrides 'language'. Use list_voices for the full catalog.
languageNoLanguage code: 'pt' (Brazilian Portuguese, default), 'en', 'en-gb', 'es', 'fr', 'it', 'hi', 'ja', 'zh'. Used to pick a default voice when 'voice' is omitted.pt
output_formatNo'audio' (default) returns playable MCP audio content; 'base64_json' returns JSON with the base64-encoded WAV plus metadataaudio

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already indicate read-only and idempotent behavior. Description adds useful context: returns WAV format, neural voices, metered per character, character limit. No contradiction with annotations.

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?

Very concise: intro sentence, two lines of key details, then well-organized Args and Returns sections. No superfluous content.

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?

Covers all aspects: input constraints (character limit), output formats with full return structure for base64_json, examples of voices, and cost indication. No missing information for a typical TTS tool.

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 description adds value by providing examples (voice IDs, language codes) and clarifying output_format options. Does more than just repeat 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 description clearly states the tool converts text to speech, specifies the output format (WAV, 16-bit PCM, 24 kHz mono), and distinguishes from siblings like list_voices (lists voices) and check_tts_service (checks service).

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?

Provides guidance on character limit, metered usage, and voice/language selection, but does not explicitly contrast with sibling tools or state when not to use this tool.

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

All tts toolsInspect
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

A4.4/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose: health check, listing available voices, and converting text to speech. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern in snake_case (check_tts_service, list_voices, synthesize_speech).

Tool Count4/5

3 tools is minimal but appropriate for a TTS service, covering health monitoring, voice discovery, and speech synthesis. A slight expansion could include voice details, but current set is reasonable.

Completeness4/5

The tool surface covers the core operations: check service health, list voices, and synthesize speech. Minor gaps, such as the inability to retrieve a single voice's details without listing all, but overall adequate for the stated purpose.

Resources