Skip to main content
Glama

get_voices

Retrieve a list of available voices with their capabilities and supported features for text-to-speech synthesis, enabling users to select the best fit for expressive and professional speech output.

Instructions

Get list of available voices with their capabilities and supported features

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Implementation Reference

  • MCP tool handler for 'get_voices': calls ttsServer.getVoices() and returns formatted markdown response with voices list, emotions, pacing styles, supported formats, and capabilities.
    case 'get_voices':
      const voices = ttsServer.getVoices();
      const voiceList = voices.voices.map(v => 
        `**${v.name}** (${v.voiceId}) - ${v.description}`
      ).join('\n');
      
      const emotionList = voices.emotions.map(e => 
        `**${e.emotion}** - ${e.description}`
      ).join('\n');
      
      const pacingList = voices.pacingStyles.map(p => 
        `**${p.pacing}** - ${p.description}`
      ).join('\n');
    
      return {
        content: [
          {
            type: 'text',
            text: `🎙️ **Available Voices & Capabilities**\n\n` +
                 `## Voices (${voices.voices.length})\n${voiceList}\n\n` +
                 `## Emotions (${voices.emotions.length})\n${emotionList}\n\n` +
                 `## Pacing Styles (${voices.pacingStyles.length})\n${pacingList}\n\n` +
                 `## Supported Formats\n${voices.supportedFormats.join(', ')}\n\n` +
                 `## Capabilities\n` +
                 `- **Speed Range:** ${voices.capabilities.speedRange.join(' - ')}x\n` +
                 `- **Volume Range:** ${voices.capabilities.volumeRange.join(' - ')}x\n` +
                 `- **Max Text Length:** ${voices.capabilities.maxTextLength.toLocaleString()} characters`,
          },
        ],
      };
  • Core getVoices() method in AdvancedTTSServer class: returns structured data for available voices (from AvailableVoices), emotions (VoiceEmotions), pacing styles (PacingStyles), formats (AudioFormats), and capabilities.
    getVoices() {
      return {
        success: true,
        voices: Object.entries(AvailableVoices).map(([id, info]) => ({
          voiceId: id,
          name: info.name,
          gender: info.gender,
          description: info.description,
          language: 'en-us',
          sampleRate: 24000,
          quality: 'high'
        })),
        emotions: Object.entries(VoiceEmotions).map(([key, value]) => ({
          emotion: key,
          description: value.description
        })),
        pacingStyles: Object.entries(PacingStyles).map(([key, value]) => ({
          pacing: key,
          description: value.description
        })),
        supportedFormats: [...AudioFormats],
        capabilities: {
          speedRange: [0.25, 3.0],
          volumeRange: [0.1, 2.0],
          maxTextLength: this.config.maxTextLength
        }
      };
    }
  • Tool registration in ListToolsRequestSchema handler: defines 'get_voices' tool with description and empty inputSchema (no required parameters).
    {
      name: 'get_voices',
      description: 'Get list of available voices with their capabilities and supported features',
      inputSchema: {
        type: 'object',
        properties: {},
      },
    },
  • Input schema for 'get_voices' tool: empty object schema indicating no input parameters are required.
      inputSchema: {
        type: 'object',
        properties: {},
      },
    },
  • Hardcoded AvailableVoices constant providing voice metadata used by getVoices() to populate the voices list.
    const AvailableVoices = {
      af_heart: { name: 'Heart', gender: 'female', description: 'Warm, friendly female voice' },
      af_sky: { name: 'Sky', gender: 'female', description: 'Clear, bright female voice' },
      af_bella: { name: 'Bella', gender: 'female', description: 'Elegant, sophisticated female voice' },
      af_sarah: { name: 'Sarah', gender: 'female', description: 'Professional, confident female voice' },
      af_nicole: { name: 'Nicole', gender: 'female', description: 'Gentle, soothing female voice' },
      am_adam: { name: 'Adam', gender: 'male', description: 'Strong, authoritative male voice' },
      am_michael: { name: 'Michael', gender: 'male', description: 'Friendly, approachable male voice' },
      bf_emma: { name: 'Emma', gender: 'female', description: 'Young, energetic female voice' },
      bf_isabella: { name: 'Isabella', gender: 'female', description: 'Mature, expressive female voice' },
      bm_lewis: { name: 'Lewis', gender: 'male', description: 'Deep, resonant male voice' },
    } as const;
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions what information is returned but doesn't address important behavioral aspects like whether this is a read-only operation, if there are rate limits, authentication requirements, or what format the response takes. The description provides basic output content but lacks operational context needed for safe invocation.

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 a single, efficient sentence that communicates the essential information without any wasted words. It's front-loaded with the core purpose and adds specific detail about what's included in the response. Every word earns its place in this compact description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a parameterless read operation with no output schema, the description provides adequate but minimal information. It tells what the tool does and what information it returns, but doesn't address format, structure, or behavioral constraints. Given the lack of annotations and output schema, more detail about response format or operational considerations would improve completeness for this type of 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?

The tool has 0 parameters with 100% schema description coverage, so the schema already fully documents the parameter situation. The description appropriately doesn't discuss parameters since none exist, and it focuses instead on what the tool returns. This meets the baseline expectation for parameterless tools while adding value about the return content.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb ('Get') and resource ('list of available voices'), making the purpose immediately understandable. It adds specificity about what information is returned ('capabilities and supported features'), which goes beyond just listing voices. However, it doesn't explicitly differentiate from sibling tools like 'list_output_files' or 'get_status', which prevents a perfect score.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives like 'synthesize_speech' or 'batch_synthesize'. There's no mention of prerequisites, typical use cases, or when this tool would be appropriate versus when other tools might be better suited. The agent must infer usage context from the tool name alone.

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

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/samihalawa/advanced-tts-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server