text-to-speech

You can convert text to natural speech audio instantly using the text-to-speech function, which eliminates the need for manual voiceover recording by generating high-quality narration directly from your script.

You can browse and filter HeyGen Starfish TTS voices by language and gender to find the perfect natural-sounding match for your multilingual narration or podcast content.

Yes, you can customize speech generation by adjusting speed and pitch, placing pauses, and selecting specific voices directly within your video production workflow without external audio tools.

No, you do not need external audio tools to create podcast content from text. The Skill generates high-quality speech audio with pause control and timestamped output directly within your existing environment.

You get timestamped audio output for synchronizing voiceovers to video by generating speech audio from text input, which provides timestamped output to assist with synchronization tasks.

The limitation is that voice generation is restricted to the available HeyGen Starfish TTS API voices, meaning you cannot import custom recorded audio or manually edit audio waveforms within the tool.