Skip to main content
similarity sets how closely an instant voice follows the recording it was cloned from. Higher levels keep more of the speaker’s character, and more of the recording’s room sound. Lower levels give the voice more room to adapt its delivery. You set it once, when you create the clone with POST /v3/models/audio/voices.

Listen

One 45-second recording, cloned four times with a different similarity each time. All four clones speak the same script with heygen-voice-1, in English, with expressiveness_boost: 0.

Source recording

Welcome back. Today, we will walk through your project settings, review the latest changes, and make sure everything is ready before you share your next video.

medium

high

extra_high

max

Listen for vocal character, phrasing, and how much of the room comes through.

Create a clone at a level

Wait until the voice is ACTIVE, then pass its voice_id to Text to Speech. An instant voice keeps the level it was created with. To hear another level, create a new clone from the same recording; each clone has its own voice_id.

Tips

  • Record in a quiet room without echo. extra_high and max keep more of the recording’s room sound than medium.
  • To compare levels, keep the recording, text, language, and remove_background_noise the same, and send the same expressiveness_boost in every speech request. Try a few short passages.
  • For the closest match to the original speaker, use max and send expressiveness_boost: 0.0.
  • For HeyGen videos, our preferred combination is max with expressiveness_boost: 0.5.
  • An image of the speaker’s setting changes the voice’s ambience. Keep it the same, or leave it out, while you compare levels.