HeyGen Text-to-Speech
Generates high-quality speech audio from text using HeyGen's Starfish TTS model for narrations, podcasts, and localized voiceovers.
This skill integrates HeyGen's advanced Starfish engine into Claude Code, allowing developers to generate professional standalone audio files directly from text. It moves beyond simple conversion by offering granular control over voice selection, speed, and pitch, alongside support for multilingual locales. Whether you are building automated voiceover workflows or generating synchronized audio for applications, this skill provides the necessary tools, including word-level timestamps and SSML-style break tags for natural-sounding pauses.
Características Principales
01Word-level timestamping for precise caption and animation syncing
02High-fidelity audio generation using the HeyGen Starfish model
03Granular audio control via speed, pitch, and locale adjustments
04Extensive voice library filtering by language, gender, and type
05SSML break tag support for realistic speech pacing and pauses
0699 GitHub stars
Casos de Uso
01Generating localized audio assets for multilingual applications and interfaces
02Building accessibility features by converting written content into high-quality speech
03Automating the creation of professional voiceovers for marketing and training content