skills.rest
beyonai
beyonaiCOMMUNITY
Explore all skills by this author →
GitHub

podcast-voice

Converts podcast script JSON files into dual-channel MP3 audio with sentence-level timing metadata.

45|11|Updated Mar 17, 2026
Search Tags:#automation#audio#podcast#tts#speech synthesis#volcengine
One-click install
npx skills add https://github.com/beyonai/ByClaw --skill podcast-voice
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: podcast-voice
Source: https://github.com/beyonai/ByClaw/tree/main/middleware/openclaw/skills/podcast-voice
Command: npx skills add https://github.com/beyonai/ByClaw --skill podcast-voice

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the manual, time-consuming process of recording and editing podcast audio by automating high-quality speech synthesis from text scripts.

Core Features & Use Cases

  • Dual-Voice Synthesis: Automatically assigns distinct voices to hosts and guests for a natural conversational flow.
  • Precision Timing: Generates sentence-level timestamps essential for synchronizing subtitles and visual slides in video production.
  • Use Case: If you have a written podcast script, this skill will generate a fully produced MP3 file with precise timing data, allowing you to instantly create a synchronized video podcast without manual audio editing.

Quick Start

Use the podcast-voice skill to generate audio for the current podcast project script.

Frequently Asked Questions about podcast-voice

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

FAQPage Schema
How do I convert a podcast script into dual-voice audio?▼

You convert a podcast script into dual-voice audio by processing structured JSON files through the Volcengine TTS API, which automatically assigns distinct voices to hosts and guests to generate a dual-channel MP3.

Does automated speech synthesis generate timing metadata for video subtitles?▼

Yes, automated speech synthesis generates sentence-level timestamp metadata alongside the MP3 audio. This precision timing is essential for synchronizing subtitles and visual slides in downstream video production pipelines.

Do I need ffmpeg and API credentials to generate TTS podcast audio?▼

You need ffmpeg installed for local audio processing and valid API credentials for the Volcengine speech service to authenticate and execute TTS podcast audio generation.

What is the best way to automate dual-voice speech synthesis for podcasts?▼

The best way to automate dual-voice speech synthesis is using a script-driven skill that supports automated versioning and concurrency-controlled synthesis via the Volcengine TTS API to streamline production.

Can I use structured JSON scripts for automated podcast audio versioning?▼

Yes, you can use structured JSON scripts for automated podcast audio versioning. The skill processes these JSON files to manage synthesis tasks and output versioned dual-channel audio and metadata.

Related Skills

Explore More Content & Communication Skills→
gman-roboticsgman-robotics

podcast-generation

Generates MP3 podcast audio and markdown transcripts from text using Volcengine TTS API.

Official
Intermediate
yudameyudame
2

podcast-audio-processing

Convert podcast audio to MP3, transcribe locally with Whisper, and embed chapter metadata.

Official
Intermediate
buda-aibuda-ai
25

audio-extractor

Extract and enhance audio from video files for MP3/WAV/AAC output.

Official
Intermediate
akrindevakrindev
4

gemini-tts

Generates speech from text using Google Gemini TTS models via Python scripts.

Community
Intermediate