skills.rest
het8802
het8802COMMUNITY
Explore all skills by this author →
GitHub

text-to-speech

Convert text to speech audio using HeyGen's Starfish TTS model.

3|1|Updated May 29, 2026
Search Tags:#text-to-speech#voice generation#HeyGen#audio creation#AI narration
One-click install
npx skills add https://github.com/het8802/OpenNolan --skill text-to-speech-het8802
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: text-to-speech
Source: https://github.com/het8802/OpenNolan/tree/main/.agents/skills/text-to-speech
Command: npx skills add https://github.com/het8802/OpenNolan --skill text-to-speech-het8802

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the generation of speech audio from text, providing control over voice, speed, and pitch, suitable for voiceovers, narration, and podcasts.

Core Features & Use Cases

  • Text to Speech: Convert written text into spoken audio using HeyGen's Starfish TTS model.
  • Voice Selection: Choose from a variety of available voices with different languages and genders.
  • Speed and Pitch Control: Adjust the speed and pitch of the generated speech.
  • Use Case: Use this Skill to create voiceovers for videos, narrate e-books, or generate audio content for podcasts.

Quick Start

Generate speech audio from the text "Hello, welcome to the demonstration." using the voice with ID "YOUR_VOICE_ID".

Frequently Asked Questions about text-to-speech

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

FAQPage Schema
How do I generate AI voiceovers from text using HeyGen?▼

You can create AI narration by sending text to HeyGen's Starfish TTS model through this Skill. It converts your written input into spoken audio, allowing you to select specific voice IDs, and adjust speed and pitch for tailored audio output.

Can I control the speed and pitch of generated speech audio?▼

Yes, you can control both speed and pitch of the generated speech audio. The Skill passes these parameters directly to the HeyGen Starfish TTS model, allowing precise adjustment for voiceovers, e-books, or podcast content.

Do I need a HeyGen API key to create text-to-speech audio?▼

Yes, a HeyGen API key is required to create text-to-speech audio. The Skill requires HeyGen API authentication to access endpoints for listing available voices and generating speech using the Starfish TTS model.

How do I list available voices for AI narration?▼

To list available voices for AI narration, the Skill queries specific HeyGen API endpoints. This retrieves a variety of voices across different languages and genders, allowing you to select the optimal voice ID for your text-to-speech task.

What is the best way to automate podcast audio creation from written content?▼

The best way to automate podcast audio creation is using this Skill to convert written text into spoken audio. By leveraging HeyGen's Starfish TTS model, you can generate voiceovers with customized speed, pitch, and selected voices.

Related Skills

Explore More Content & Communication Skills→
47thtechcorner47thtechcorner
21

text-to-speech

Convert text into speech audio files using the HeyGen Starfish TTS model.

Community
Intermediate
Will-GoWill-Go

hyperframes-media

Automate text-to-speech, transcription, and background removal for multimedia assets.

Community
Intermediate
abdu6666abdu6666
17

digital-human-integrator

Integrates AI digital human avatars into video content via D-ID, Synthesia, or HeyGen.

Community
Advanced
gyalamanch001agyalamanch001a

text-to-speech

Generate speech audio from text using HeyGen Starfish TTS.

Community
Intermediate