skills.rest
dangngocbinh
dangngocbinhCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

Voice Generation

Generate speech audio and metadata JSON from text via multiple providers.

2|1|Updated Jan 24, 2026
Search Tags:#video#text-to-speech#emotion#timestamps#multi-provider#voice-generation
One-click install
npx skills add https://github.com/dangngocbinh/vibedio --skill voice-generation-dangngocbinh
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Voice Generation
Source: https://github.com/dangngocbinh/vibedio/tree/main/.claude/skills/voice-generation
Command: npx skills add https://github.com/dangngocbinh/vibedio --skill voice-generation-dangngocbinh

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires fs-extra, axios, dotenv, minimist, openai, @google-cloud/text-to-speech, form-data, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the production of natural-sounding voiceovers from text, enabling rapid video narration without hiring voice actors or recording sessions.

Core Features & Use Cases

  • Multi-provider support: ElevenLabs, Vbee, OpenAI, and Gemini for flexible voice options.
  • Emotion-aware voices: map text sentiment to voices and prosody for engaging narration.
  • Timestamps and transcripts: generate word-level timestamps to improve subtitles and searchability.
  • Script-driven workflows: use --text-path or --script inputs and generate corresponding audio and metadata.

Quick Start

Use the voice-generation skill to render speech from a text file or script and store outputs in a project folder. Example: node .claude/skills/voice-generation/scripts/generate-voice.js --text-path "public/projects/my-video/raw_script.txt" --provider "elevenlabs" --emotion "happy" --outputDir "public/projects/my-video"

Frequently Asked Questions about Voice Generation

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

FAQPage Schema
How do I generate natural voiceovers from text for video production?▼

To generate natural voiceovers from text, use a multi-provider text-to-speech script that processes text via --text-path or --script inputs, producing audio files and metadata JSON for video narration.

Does text-to-speech support emotion control and word-level timestamps?▼

Yes, emotion-aware voice generation maps text sentiment to specific voices and prosody, while also generating word-level timestamps to improve subtitle alignment and searchability.

Can I use ElevenLabs, OpenAI, or Gemini for voice generation?▼

Yes, the voice generation workflow supports multiple providers including ElevenLabs, Vbee, OpenAI, and Gemini, requiring corresponding API keys in a .env file for flexible voice selection.

What is the best way to automate Vietnamese and English voice narration?▼

The best way to automate English and Vietnamese voice narration is using a script-driven text-to-speech workflow that processes text files and outputs audio files with language-specific provider support.

Do I need API keys to generate speech from a script file?▼

Yes, you must configure environment keys such as ELEVENLABS_API_KEY, VBEE_API_KEY, OPENAI_API_KEY, or GEMINI_API_KEY in a .env file before generating speech from script files.

What are the limitations of using multi-provider text-to-speech for videos?▼

Limitations include dependency on external provider API keys for each specific service, and output is restricted to audio files and metadata JSON without direct video editing integration.

Related Skills

Explore More Content & Communication Skills→
LaiTszKinLaiTszKin
4

docs-to-voice

Convert text to audio with sentence timelines and subtitle files.

Community
Advanced
MatrixReligioMatrixReligio
39

subtitles

Generate synchronized bilingual subtitles from voiceover_metadata.json for Remotion video projects.

Official
Intermediate
AbsolutelySkilledAbsolutelySkilled
207

video-creator

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

Official
Advanced
X-School-AcademyX-School-Academy
19

media-text-segments-to-speech

Generate WAV speech audio from text segments with emotion and voice controls.

Official
Intermediate