batch_synthesize
Transform multiple text segments into audio with customizable voice, speed, emotion, and pacing. Optionally merge segments into a single file for efficient TTS processing.
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"
}