# HeyGen Voice STS carries a spoken take onto an avatar

By Steven Van · 2026-10-28

Say a line once and HeyGen uses that timing on an avatar. The speech-to-speech API costs $0.12 a minute and returns audio only.

[HeyGen](<https://creatorstoolbox.com/tools/heygen>) announced Voice STS on October 28. You say a line once, and HeyGen says the avatar keeps the performance, down to pauses, emphasis, and whispers. A test page is live on the HeyGen platform.

[View media](<https://video.twimg.com/amplify_video/2115497694898831360/vid/avc1/1920x1080/1eHBsRT8r1PlZztA.mp4>)

Official HeyGen announcement demo.

The help center, updated the same day, calls the Studio workflow Voice Mirroring. You record in Studio or upload an MP3 or WAV up to 100 MB, turn mirroring on, and the voice selected for the avatar speaks with your timing. HeyGen transcribes the recording so you can check the words.

The Speech to Speech API is billed at $0.12 per minute and returns a WAV. It does not lip-sync an avatar by itself; you pass that audio into a video request. Professional voice clones are not supported on the API yet. The help article describes pacing, emphasis, and pauses, and does not mention whispers.

Sources

[HeyGen’s announcement and demo](<https://x.com/HeyGen/status/2115497751731716508>), [How to use Speech to Speech](<https://help.heygen.com/en/articles/17756130-how-to-use-speech-to-speech-voice-mirroring-in-heygen>), [the speech-to-speech test page](<https://platform.heygen.com/speech-to-speech>).

[Read HeyGen Voice STS carries a spoken take onto an avatar on Creators Toolbox](<https://creatorstoolbox.com/blog/heygen-voice-sts-avatars>)

---
Canonical source: https://creatorstoolbox.com/blog/heygen-voice-sts-avatars