skills.rest
liancheng-zcy
liancheng-zcyCOMMUNITY
Explore all skills by this author →
GitHub

tts-voiceover

Generate 48kHz mono WAV voiceovers from text using VoxCPM2.

96|19|Updated Mar 16, 2026
Search Tags:#tts#voice cloning#voiceover#remotion#local processing#wav generation#batch tts
One-click install
npx skills add https://github.com/liancheng-zcy/remotion-com-skills --skill tts-voiceover
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tts-voiceover
Source: https://github.com/liancheng-zcy/remotion-com-skills/tree/main/.claude/skills/tts-voiceover
Command: npx skills add https://github.com/liancheng-zcy/remotion-com-skills --skill tts-voiceover

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It solves the problem of producing high-quality narrated voiceovers from text without relying on external online TTS services.

Core Features & Use Cases

  • Local voice cloning and voice design: Generate narration using VoxCPM2 with either reference-audio cloning or description-based voice design.
  • Complete end-to-end workflow: Guides users to locate the VoxCPM2 TTS integration folder, configure reference audio when needed, run the correct generation mode, and save outputs.
  • Batch generation for scripts: Convert multiple lines of text into separate WAV files efficiently for longer video scripts.
  • Remotion-ready outputs: Produces 48kHz mono WAV suitable for video narration pipelines.

Quick Start

Tell me the path to your VoxCPM2 TTS integration folder and the WAV reference audio you want to clone (or confirm you want voice design), and I will generate the voiceover and save the output WAV.

Frequently Asked Questions about tts-voiceover

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

FAQPage Schema
How do I generate voiceover audio locally without relying on online TTS services?▼

Local voiceover generation uses a local VoxCPM2 TTS integration directory to process text into audio. This allows you to produce high-quality 48kHz mono WAV narration files entirely offline.

Can I clone a specific voice for my Remotion video narration?▼

Voice cloning for Remotion narration is supported by providing a reference WAV audio file to the local VoxCPM2 integration. The system uses this reference to generate matching voiceover audio.

How do I convert a multi-line script into separate WAV files for batch voice generation?▼

Batch voice generation converts multiple lines of text into separate 48kHz mono WAV files. You use batch mode to efficiently process longer video scripts into individual audio outputs.

Do I need reference audio to design a voice, or can I generate narration without it?▼

Reference audio is optional for voice design. You can use description-based voice design mode to generate narration without providing a reference WAV file for cloning.

What audio format does the local TTS system output for video narration pipelines?▼

The local TTS system outputs 48kHz mono WAV files. This format is specifically produced to be Remotion-ready and suitable for integration into video narration pipelines.

What is description-based voice design and when should I use it instead of cloning?▼

Description-based voice design generates narration from text descriptions rather than reference audio. Use this mode when you lack a reference WAV file or need a custom voice profile.

Related Skills

Explore More Content & Communication Skills→
abhiunixabhiunix
1

sherpa-onnx-tts

Synthesize text to WAV files offline using sherpa-onnx-tts CLI.

Community
Intermediate
AbsolutelySkilledAbsolutelySkilled
207

video-creator

Coordinate a seven-step video production workflow from script to 4K render.

Official
Advanced
elevenlabselevenlabs
412

text-to-speech

Convert text into natural-sounding speech using ElevenLabs voice AI.

Official
Intermediate
EmZodEmZod
8

speak-tts

Generate speech from text with on-device TTS and voice cloning on Apple Silicon.

Community
Advanced