text-to-speech

Convert text to natural-sounding speech by using the HeyGen Starfish TTS model to generate audio with adjustable speed, pitch, and locale settings. You provide the text, select a voice by language and gender, and call the audio endpoint to receive the generated voiceover file.

Yes, you can list available TTS voices filtered by language and gender. The Skill exposes an API that queries the HeyGen Starfish voice catalog, allowing you to retrieve and select specific voice profiles matching your desired locale and gender before generating audio.

Adjust speed and pitch when generating audio by specifying the desired parameters in your request to the HeyGen Starfish TTS endpoint. This allows you to control the delivery rate and tone of the selected voice to achieve natural-sounding speech output.

Yes, the text-to-speech API returns word timestamps alongside the audio URL and duration. This provides precise timing data for each spoken word, which is essential for synchronizing voiceovers with video production pipelines or standalone audio workflows.

No, you do not need an existing audio file. The Skill generates audio content directly from input text using the HeyGen Starfish TTS model, completely eliminating the need to manually record voiceovers for podcasts, videos, or multilingual content.