batch_synthesize

batch_synthesize

Generate and optionally merge multiple synthesized speech segments using configurable voice, speed, emotion, pacing, and pause settings for professional text-to-speech applications.

Instructions

Synthesize multiple text segments with optional merging and intelligent pacing

Input Schema

Name	Required	Description	Default
`emotion`	No	Voice emotion for all segments	neutral
`filename`	No	Custom filename for saved audio
`mergeOutput`	No	Merge segments into single file
`outputFormat`	No	Audio output format	wav
`pacing`	No	Speech pacing style for all segments	natural
`saveFile`	No	Save audio to file
`segmentPause`	No	Pause between segments in seconds
`segments`	Yes	List of text segments to synthesize
`speed`	No	Speech speed (0.25-3.0)
`voiceId`	No	Voice to use for all segments	af_heart

Input Schema (JSON Schema)

{
  "properties": {
    "emotion": {
      "default": "neutral",
      "description": "Voice emotion for all segments",
      "enum": [
        "neutral",
        "happy",
        "excited",
        "calm",
        "serious",
        "casual",
        "confident"
      ],
      "type": "string"
    },
    "filename": {
      "description": "Custom filename for saved audio",
      "type": "string"
    },
    "mergeOutput": {
      "default": true,
      "description": "Merge segments into single file",
      "type": "boolean"
    },
    "outputFormat": {
      "default": "wav",
      "description": "Audio output format",
      "enum": [
        "wav",
        "mp3",
        "flac",
        "ogg"
      ],
      "type": "string"
    },
    "pacing": {
      "default": "natural",
      "description": "Speech pacing style for all segments",
      "enum": [
        "natural",
        "conversational",
        "presentation",
        "tutorial",
        "narrative",
        "fast",
        "slow"
      ],
      "type": "string"
    },
    "saveFile": {
      "default": false,
      "description": "Save audio to file",
      "type": "boolean"
    },
    "segmentPause": {
      "default": 0.5,
      "description": "Pause between segments in seconds",
      "maximum": 5,
      "minimum": 0,
      "type": "number"
    },
    "segments": {
      "description": "List of text segments to synthesize",
      "items": {
        "type": "string"
      },
      "minItems": 1,
      "type": "array"
    },
    "speed": {
      "default": 1,
      "description": "Speech speed (0.25-3.0)",
      "maximum": 3,
      "minimum": 0.25,
      "type": "number"
    },
    "voiceId": {
      "default": "af_heart",
      "description": "Voice to use for all segments",
      "enum": [
        "af_heart",
        "af_sky",
        "af_bella",
        "af_sarah",
        "af_nicole",
        "am_adam",
        "am_michael",
        "bf_emma",
        "bf_isabella",
        "bm_lewis"
      ],
      "type": "string"
    }
  },
  "required": [
    "segments"
  ],
  "type": "object"
}

Advanced TTS MCP Server

Instructions

Input Schema

Input Schema (JSON Schema)

Other Tools from Advanced TTS MCP Server

Related Tools

MCP directory API