skills.rest
CatfishW
CatfishWCOMMUNITY
Explore all skills by this author →
GitHub

text2speech

Generate speech from text using Qwen3-TTS models with preset speakers and voice cloning.

Updated Feb 12, 2026
Search Tags:#text-to-speech#audio synthesis#tts#voice generation#qwen3-tts#voice clone
One-click install
npx skills add https://github.com/CatfishW/TTSAgentSkill --skill text2speech
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text2speech
Source: https://github.com/CatfishW/TTSAgentSkill/tree/main
Command: npx skills add https://github.com/CatfishW/TTSAgentSkill --skill text2speech

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of converting written text into spoken audio, enabling applications that require voice output, such as accessibility tools, virtual assistants, and content creation.

Core Features & Use Cases

  • Text-to-Speech Generation: Convert any text into natural-sounding speech using advanced AI models.
  • Voice Customization: Choose from preset speakers, design unique voices from descriptions, or clone voices from audio samples.
  • Batch Processing: Efficiently generate audio for multiple text inputs simultaneously.
  • Use Case: A content creator can use this Skill to generate voiceovers for their videos directly from scripts, saving time and resources.

Quick Start

Use the text2speech skill to speak the phrase "Hello world" using the vivian speaker and save it to a file named hello.wav.

Frequently Asked Questions about text2speech

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech using a custom voice clone?▼

To convert text to speech using a custom voice clone, provide your text and an audio sample to the model. The Skill supports voice cloning from audio or timbre, synthesizing natural speech that matches the provided voice characteristics.

Can I generate voiceovers for multiple text scripts at once?▼

Yes, you can generate voiceovers for multiple text scripts at once. The Skill supports batch processing, allowing you to efficiently synthesize audio for multiple text inputs simultaneously and save time on content creation.

Does text-to-speech generation support creating a voice from a text description?▼

Text-to-speech generation does support creating a voice from a text description. The Skill includes voice design capabilities, allowing you to define unique voice characteristics by describing them instead of using preset speakers.

What do I need to use Qwen3-TTS for audio synthesis in my project?▼

To use Qwen3-TTS for audio synthesis, you need a Python environment with the `requests` library installed. The Skill integrates with a TTSWeb API to handle the audio tokenization, decoding, and voice generation processes.

How does voice generation handle saving the output to a file?▼

Voice generation handles saving output by processing your text through the TTSWeb API and writing the decoded audio stream to a specified file format. You can easily save the generated speech as a WAV file for immediate use.

Related Skills

Explore More Content & Communication Skills→
kortix-aikortix-ai
6

elevenlabs

Generate speech, cloned voices, and sound effects via the ElevenLabs API.

Official
Intermediate
TheArchitectitTheArchitectit
3

audio-gen

Unify text-to-speech, transcription, audio conversion, and editing workflows.

Community
Intermediate
tsaijameytsaijamey
60

frago-video-production

Automate video production from research to final FFmpeg merge.

Community
Advanced
openclaw-easyopenclaw-easy
14

sherpa-onnx-tts

Convert input text to speech locally using sherpa-onnx and ONNX models.

Community
Intermediate