tts
0The tts skill converts any text into speech audio using two backends (Kokoro local and Noiz cloud). It supports features like voice cloning and timeline-accurate audio synthesis for dubbing and video narration.
51100Updated 2mo ago
Text-to-Speech
Quick InstallView Source
$ npx skills add https://github.com/noizai/skills --skill ttsOverview
About This Skill
The tts skill converts text into natural-sounding speech audio using two backends: Kokoro for local, privacy-first processing, and Noiz for cloud-based generation with advanced features. It supports precise duration control and timeline-aligned rendering, making it ideal for video dubbing, narration, and content creation workflows. The skill includes voice cloning capabilities powered by reference audio, allowing you to generate speech in specific voices. Setup requires either a local Kokoro installation or a Noiz API key for cloud processing, with the option to control emotion and speaking style through the characteristic-voice skill integration.
How to Use
Install via `$ npx skills add https://github.com/noizai/skills --skill tts`
Use Cases
Convert text, files, or URLs to audio with voice cloning.
Align speech to SRT subtitles for video narration.
Control voice selection, language, and emotion in segments.
Tags
Setup & Installation
Quick Install
Terminal
$ npx skills add https://github.com/noizai/skills --skill ttsAlternative Install (Git Clone)
git clone https://github.com/noizai/skillsRequirements
- Claude Code or compatible AI agent
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Convert the following text to speech using the tts skill: '[TEXT_TO_CONVERT]'. Use the [BACKEND] backend ([Kokoro_LOCAL/Noiz_CLOUD]). If voice cloning is needed, specify the cloned voice with '[VOICE_NAME]' or 'default'. For timeline-accurate synthesis, include the timing markers in the format '[SYNC:TIMESTAMP]' where TIMESTAMP is in seconds.
Example Output
### Audio Output Here’s the synthesized speech for your text: ``` [SYNC:0.0] Welcome to the [COMPANY] annual report for [YEAR]. [SYNC:2.5] Today, we'll review our progress in the [INDUSTRY] sector. [SYNC:5.0] Key highlights include a 12% increase in revenue and a 15% reduction in operational costs. ``` **Backend Used:** Noiz Cloud **Voice:** Default (Female, Neutral Tone) **Duration:** 8.2 seconds *Download the audio file here: [LINK_TO_AUDIO_FILE]* Would you like to adjust the voice, backend, or timing markers for further refinement?
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan