skills.rest
kuettai
kuettaiCOMMUNITY
Explore all skills by this author →
GitHub

narrative-voice-generation

Generate multi-voice narrated audio files using Amazon Polly neural voices and SSML.

4|Updated May 4, 2026
Search Tags:#storytelling#voice#audio#narration#polly#ssml#multivoice
One-click install
npx skills add https://github.com/kuettai/unlock-cloud --skill narrative-voice-generation
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: narrative-voice-generation
Source: https://github.com/kuettai/unlock-cloud/tree/main/.kiro/skills/narrative-voice
Command: npx skills add https://github.com/kuettai/unlock-cloud --skill narrative-voice-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires boto3, json, os, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill simplifies the creation of multi-voice audio narratives for storytelling and educational content, saving time and enhancing engagement.

Core Features & Use Cases

  • Voice Mapping: Define characters with specific voice profiles for coherent dialogue playback.
  • Segment Structuring: Organize narrative parts with timing and emphasis controls for natural speech flow.
  • Use Case: Generate narrated episodes or tutorials where different characters or roles speak using natural-sounding Amazon Polly voices, such as a narrator, system alerts, or characters.
  • Audio Synthesis: Convert structured narrative JSON into high-quality speech files for playback or distribution.

Quick Start

Use the narrative-voice skill to generate speech audio files from your narrative scenario JSON files in the scenarios folder by running the provided script.

Frequently Asked Questions about narrative-voice-generation

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

FAQPage Schema
How do I generate multi-voice audio narration for storytelling?▼

Generate multi-voice audio narration by mapping characters to specific Amazon Polly neural voice profiles and processing structured narrative JSON to produce high-quality speech files.

What is SSML and how is it used for cinematic speech in audio synthesis?▼

SSML, or Speech Synthesis Markup Language, is used to control segment timing and emphasis in narrative scripts, enabling natural speech flow and cinematic formatting in synthesized audio.

Can I use Amazon Polly voices for character dialogue in automated tutorials?▼

Yes, you can assign specific Amazon Polly neural voices to different characters or roles, enabling coherent multi-voice dialogue playback for narrated tutorials and immersive episodes.

How do I structure a narrative JSON file for audio speech synthesis?▼

Structure your narrative JSON by defining character voice mappings and organizing narrative segments with specific timing and emphasis controls to achieve natural speech flow.

Do I need an AWS account to use Amazon Polly for audio file generation?▼

Yes, because the skill relies on the boto3 dependency to interact with Amazon Polly neural voices, requiring configured AWS credentials to synthesize and output speech audio files.

Related Skills

Explore More Content & Communication Skills→
ToanPV90ToanPV90

aws-secrets-manager

Store and rotate sensitive credentials in AWS Secrets Manager.

Community
Advanced
adiytharpansaadiytharpansa

sag

Convert written text into expressive speech using ElevenLabs text-to-speech.

Community
Intermediate
0xsline0xsline
907

voice

Generate text-to-speech audio and sound effects synchronized with video timelines.

Community
Advanced
WarrenZhu050413WarrenZhu050413
7

generating-tts

Generate and play multilingual text-to-speech audio with adjustable voices and speeds.

Community
Intermediate