Skip to main content
Glama

text_to_audio

Convert text descriptions into AI-generated audio content including sound effects, ambient sounds, music, and atmospheric soundscapes.

Instructions

Generate AI-powered audio content from text descriptions using MMAudio technology. Create sound effects, ambient audio, music, and atmospheric soundscapes from natural language descriptions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesDescribe the audio you want to generate (e.g., "rain falling on leaves", "coffee shop ambiance", "futuristic sci-fi sounds")
durationNoDuration of generated audio in seconds
num_stepsNoNumber of inference steps (higher = better quality, slower)
cfg_strengthNoClassifier-free guidance strength (higher = more adherence to prompt)
negative_promptNoDescribe what you want to avoid in the generated audio (optional)
seedNoRandom seed for reproducible results

Implementation Reference

  • Executes the text_to_audio tool: validates input, calls external MMAudio API, handles errors, validates response, and returns audio generation result.
    async handleTextToAudio(args) { this.ensureConfigured(); try { const input = TextToAudioInputSchema.parse(args); console.error(`[MMAudio] Starting text-to-audio generation for prompt: "${input.prompt}"`); const response = await fetch(`${this.config.baseUrl}/api/text-to-audio`, { method: 'POST', headers: { 'Content-Type': 'application/json', 'Authorization': `Bearer ${this.config.apiKey}`, 'User-Agent': 'MMAudio-MCP/1.0.0', }, body: JSON.stringify(input), timeout: this.config.timeout, }); if (!response.ok) { const errorText = await response.text(); let errorMessage = `HTTP ${response.status}`; try { const errorData = JSON.parse(errorText); errorMessage = errorData.error || errorMessage; } catch { errorMessage = errorText || errorMessage; } if (response.status === 401) { throw new McpError(ErrorCode.InvalidRequest, 'Invalid API key. Please check your MMAudio API key.'); } else if (response.status === 403) { throw new McpError(ErrorCode.InvalidRequest, 'Insufficient credits for text-to-audio generation.'); } else if (response.status === 429) { throw new McpError(ErrorCode.InvalidRequest, 'Rate limit exceeded. Please try again later.'); } throw new Error(errorMessage); } const result = await response.json(); const validatedResult = TextToAudioResponseSchema.parse(result); console.error(`[MMAudio] Text-to-audio generation completed successfully`); return { content: [ { type: 'text', text: JSON.stringify({ success: true, message: 'Audio generated successfully from text', result: { audio_url: validatedResult.audio.url, content_type: validatedResult.audio.content_type, file_name: validatedResult.audio.file_name, file_size: validatedResult.audio.file_size, duration: input.duration, prompt: input.prompt, } }, null, 2), }, ], }; } catch (error) { if (error instanceof z.ZodError) { throw new McpError( ErrorCode.InvalidParams, `Invalid input parameters: ${error.errors.map(e => `${e.path.join('.')}: ${e.message}`).join(', ')}` ); } throw error; } }
  • Zod input schema for validating parameters of the text_to_audio tool.
    const TextToAudioInputSchema = z.object({ prompt: z.string().min(1, 'Prompt is required'), duration: z.number().min(1).max(30).default(8), num_steps: z.number().int().min(1).max(50).default(25), cfg_strength: z.number().min(1).max(10).default(4.5), negative_prompt: z.string().optional().default(''), seed: z.number().int().optional().default(0), });
  • MCP tool registration in the ListTools response, including name, description, and input schema definition.
    { name: 'text_to_audio', description: 'Generate AI-powered audio content from text descriptions using MMAudio technology. Create sound effects, ambient audio, music, and atmospheric soundscapes from natural language descriptions.', inputSchema: { type: 'object', properties: { prompt: { type: 'string', description: 'Describe the audio you want to generate (e.g., "rain falling on leaves", "coffee shop ambiance", "futuristic sci-fi sounds")', }, duration: { type: 'number', minimum: 1, maximum: 30, default: 8, description: 'Duration of generated audio in seconds', }, num_steps: { type: 'integer', minimum: 1, maximum: 50, default: 25, description: 'Number of inference steps (higher = better quality, slower)', }, cfg_strength: { type: 'number', minimum: 1, maximum: 10, default: 4.5, description: 'Classifier-free guidance strength (higher = more adherence to prompt)', }, negative_prompt: { type: 'string', description: 'Describe what you want to avoid in the generated audio (optional)', default: '', }, seed: { type: 'integer', default: 0, description: 'Random seed for reproducible results', }, }, required: ['prompt'], }, }, {
  • Zod response schema for validating the API response of text_to_audio tool (references shared AudioResponseSchema).
    const TextToAudioResponseSchema = z.object({ audio: AudioResponseSchema, });
  • Dispatch case in CallToolRequest handler that routes text_to_audio calls to the handler function.
    case 'text_to_audio': return await this.handleTextToAudio(args);

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/mmaudio/mmaudio-mcp'

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