generate_audio_script
Convert structured scripts or plain text into audio with multiple voices and actors using the ElevenLabs text-to-speech API. Supports JSON or text input for customized voice and actor assignments.
Instructions
Generate audio from a structured script with multiple voices and actors. Accepts either: 1. Plain text string 2. JSON string with format: { "script": [ { "text": "Text to speak", "voice_id": "optional-voice-id", "actor": "optional-actor-name" }, ... ] }
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| script | Yes | JSON string containing script array or plain text. For JSON format, provide an object with a 'script' array containing objects with 'text' (required), 'voice_id' (optional), and 'actor' (optional) fields. |
Input Schema (JSON Schema)
You must be authenticated.
Other Tools from ElevenLabs MCP Server
Related Tools
- @mamertofabian/elevenlabs-mcp-server
- @mamertofabian/elevenlabs-mcp-server
- @vmehta14/whissle-mcp
- @Ichigo3766/audio-transcriber-mcp
- @bigdata-coss/agent_mcp