create_flowspeech
Convert text or URL content to speech for podcast episodes using AI-enhanced processing or direct conversion modes with customizable speaker voices.
Instructions
Create a FlowSpeech episode by converting text or URL content to speech. Supports smart mode (AI-enhanced, fixes grammar) and direct mode (no modifications). This tool will automatically poll until generation is complete.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| sourceType | Yes | Source type: text or url | |
| sourceContent | Yes | Source content (text or URL) | |
| speakerId | Yes | Speaker name or ID. Use speaker name from get_speakers tool output (the "name" field, not speakerId). Full speaker ID also supported. | |
| language | No | Language code (e.g., "zh" for Chinese, "en" for English). Default: zh | |
| mode | No | Generation mode: "smart" (AI-enhanced, fixes grammar) or "direct" (no modifications) | smart |
Input Schema (JSON Schema)
{
"properties": {
"language": {
"description": "Language code (e.g., \"zh\" for Chinese, \"en\" for English). Default: zh",
"type": "string"
},
"mode": {
"default": "smart",
"description": "Generation mode: \"smart\" (AI-enhanced, fixes grammar) or \"direct\" (no modifications)",
"enum": [
"smart",
"direct"
],
"type": "string"
},
"sourceContent": {
"description": "Source content (text or URL)",
"minLength": 1,
"type": "string"
},
"sourceType": {
"description": "Source type: text or url",
"enum": [
"text",
"url"
],
"type": "string"
},
"speakerId": {
"description": "Speaker name or ID. Use speaker name from get_speakers tool output (the \"name\" field, not speakerId). Full speaker ID also supported.",
"minLength": 1,
"type": "string"
}
},
"required": [
"sourceType",
"sourceContent",
"speakerId"
],
"type": "object"
}