Ttscn
Ttscn converts Chinese and multilingual text to natural speech across 11 cloud backends, from free Edge TTS to premium providers like ElevenLabs and OpenAI. Choose by use case—short video, audiobook, enterprise SSML, or lowest cost—with support for word-level timestamps, pause markers, and pronunciation overrides.
Ttscn generates natural Chinese and multilingual speech from text via 11 cloud backends with flexible voice and quality options.
AI-generated summary based on this skill's SKILL.md
Install
Agents365-ai/365-skills/ttsCN · repository language: Python
git clone https://github.com/Agents365-ai/365-skills
cp -r 365-skills ~/.claude/skills/ttsCNgenerated, unverified - the skill's exact subdirectory could not be determined; check the repository on GitHub
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
What is ttscn?
Ttscn is a text-to-speech skill from Agents365 that converts Chinese and multilingual text into natural speech. It supports 11 cloud backends ranging from free options like Edge TTS to premium providers including ElevenLabs and OpenAI, letting you choose the right provider based on your use case—whether for short videos, audiobooks, enterprise SSML needs, or cost optimization.
What capabilities does the Ttscn skill provide?
Ttscn offers multilingual text-to-speech conversion with advanced features including word-level timestamps, pause markers, and pronunciation overrides. The skill integrates 11 different cloud backends, enabling flexible selection based on quality requirements, language support, and budget constraints for diverse applications.
How to use ttscn for different use cases?
Ttscn supports multiple use cases through its diverse backend options. For short videos, select a fast provider; for audiobooks, choose quality-focused backends; for enterprise needs requiring SSML support, use premium providers; and for budget-conscious projects, leverage free options like Edge TTS. Word-level timestamps and pronunciation overrides enhance customization.
Which text-to-speech backends does Ttscn support?
Ttscn integrates 11 cloud backends for text-to-speech conversion. These range from free services like Edge TTS to premium providers such as ElevenLabs and OpenAI. This variety allows you to select the optimal backend based on your specific requirements for quality, language support, features, and cost.
Can Ttscn handle Chinese text conversion to speech?
Yes, Ttscn specializes in converting Chinese and multilingual text to natural speech. With support for 11 cloud backends, the skill provides robust Chinese language processing alongside other languages, making it suitable for diverse multilingual applications and regional content needs.
What advanced features does the Ttscn skill include?
Ttscn includes word-level timestamps for precise audio synchronization, pause markers for natural speech pacing, and pronunciation overrides for customized output. These features, combined with backend flexibility across 11 providers, enable fine-grained control over speech synthesis quality and timing for professional applications.