text-to-speech

To convert text to speech for a voiceover, this Skill uses the HeyGen Starfish TTS model to generate high-quality audio files from your script. You simply provide the text and select a preferred voice ID to instantly create professional-grade narration.

Yes, you can adjust the pitch and speed of generated TTS audio. The Skill supports voice modulation settings alongside multilingual locale configurations, allowing you to customize the speech output to match diverse audio production needs.

Yes, you need a valid HEYGEN_API_KEY to generate narration from text. The Skill requires this key to authenticate and integrate with HeyGen's audio generation endpoints for successful speech synthesis.

The best way to create multilingual voiceovers from a script is by using a TTS Skill with multilingual locale support. You can access a wide voice library categorized by language and gender, then select a specific voice ID to match your project.

Text-to-speech audio generation fails if the HEYGEN_API_KEY is missing or invalid, as the Skill depends on HeyGen's endpoints. Ensure the requests library is installed and a correct voice ID is provided for successful synthesis.