MiniMax 多人对话语音合成

What This Skill Does

The MiniMax 多人对话语音合成 skill is a sophisticated AI agent module designed to transform text-based creative writing into high-quality, professional-grade audio productions. By integrating advanced natural language generation with high-fidelity speech synthesis models, this skill handles the end-to-end process of multi-character dialogue creation. It automatically structures narratives, analyzes character profiles to assign distinct voice IDs, performs intelligent text-to-speech synthesis with expressive emotional markers, and generates a cohesive, ready-to-use HTML presentation.

Installation

To install this skill, use the OpenClaw CLI in your terminal:

clawhub install openclaw/skills/skills/hexiaochun/sutui-minimax-tts

Ensure you have the necessary environment dependencies installed, including pydub and FFmpeg on your system to support the audio merging functionalities provided by the automation scripts.

Use Cases

This skill is perfect for content creators, developers, and educators. Use it to:

• Educational Content: Create interactive audio-based learning scripts or historical reenactments.
• Audio Dramas & Podcasts: Rapidly prototype or produce multi-character scripted audio content with varied emotional depth.
• Marketing & User Testing: Generate lifelike user personas for conversational UI testing or immersive brand storytelling.
• Accessibility: Convert long-form text or documents into structured, multi-voice audiobooks that are easier to consume.

Example Prompts

1. "生成一段关于程序员和产品经理在星巴克争论需求文档的对话，两人风格要截然不同，最后生成合成音频页面。"
2. "创建一个轻松幽默的访谈，主持人是女性，嘉宾是一位经验丰富的老中医，要求对话包含丰富的情绪表达，并生成 HTML 网页展示。"
3. "编写一段严肃的商业谈判对话剧本，角色为两位成熟商务人士，语速要求中等，并帮我处理好对应的音频合成任务。"

Tips & Limitations

• Quality Control: Always review the suggested voice mappings after the tool call to ensure the tone matches your character archetype.
• Text Preprocessing: The skill includes advanced emotional markup (like breath or laughter). Ensure your input dialogue allows for these markers to significantly improve the realism of the output.
• Limitations: The generation speed depends on the total word count of the script and server availability. Extremely long scripts (over 2000 words) should be broken into multiple chapters for best results. Always verify the output directory (dialogue_output/) after the process finishes to ensure all segments have been rendered correctly.