You can now record a line on your phone or laptop and get it back in your HeyGen Voice. Speech-to-speech keeps the emotion, timing, pacing, emphasis, and pronunciation from your recording and changes only the voice.

What’s new

• Studio-quality output from casual recordings. A rough phone take comes back as a clean, polished read in your voice clone.

• More emotional range than text prompting. Not every voice responds to emotional direction written as text. With STS, the warmth, urgency, or energy in your recording carries over to your clone, including whispers, laughs, and accents.

• Precise control over delivery. You set where the emphasis falls, how pauses land, and the cadence of the read, so you don’t have to regenerate TTS until it sounds right.

Why it matters

Say a line once the way you mean it, and your HeyGen Voice delivers it exactly that way. No studio setup, no regenerating TTS ten times, no hoping a text prompt gets the emotion right.

Available now in HeyGen and via API.