generate_podcast_audio
Convert podcast text content into audio using FlowSpeech technology. This tool processes completed text episodes into spoken audio, supporting custom scripts and speaker assignments for podcast production.
Instructions
Generate audio for a podcast episode that already has text content. This is the second stage of two-stage generation. The episode must have contentStatus=text-success. You can optionally provide customScripts parameter to override the generated scripts when generating audio. NOTE: This is the ONLY way to use modified scripts - there is no separate tool to edit scripts after generation.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| episodeId | Yes | The complete 24-character episode ID from the previous create_podcast_text_only response. IMPORTANT: Must be exactly 24 characters. Copy the FULL Episode ID - do not truncate or shorten it. | |
| customScripts | No | Optional custom scripts to override generated ones | |
| waitForCompletion | No | Whether to wait for audio generation to complete |
Input Schema (JSON Schema)
{
"properties": {
"customScripts": {
"description": "Optional custom scripts to override generated ones",
"items": {
"additionalProperties": false,
"properties": {
"content": {
"description": "Script text content",
"type": "string"
},
"speakerId": {
"description": "Speaker ID",
"type": "string"
}
},
"required": [
"content",
"speakerId"
],
"type": "object"
},
"type": "array"
},
"episodeId": {
"description": "The complete 24-character episode ID from the previous create_podcast_text_only response. IMPORTANT: Must be exactly 24 characters. Copy the FULL Episode ID - do not truncate or shorten it.",
"maxLength": 24,
"minLength": 24,
"type": "string"
},
"waitForCompletion": {
"default": true,
"description": "Whether to wait for audio generation to complete",
"type": "boolean"
}
},
"required": [
"episodeId"
],
"type": "object"
}