Skip to main content
BenchLM
Data
Official provider results

HeyGen Voice evaluation

HeyGen reports a 76.1/100 voice-clone rating from 43 people judging their own digital twins. A separate platform study gave full-clone 41.7% of 6,153 three-way preference votes.

Source snapshots refreshed
Five measurement lanesVOICE / S2S

Reasoning, task completion, conversation dynamics, experience, and latency stay separate.

Back to directory

Benchmark profile

Scope
Provider digital-twin ratings and platform clone preferences
Primary metric
Mean rating (1–100) and preference share (%)
Owner
HeyGen
Available evidence
Provider tables published October 14, 2026

What it measures

Voice experience
Is the exchange natural, robust, and responsive?

Available results

Digital-twin rating · voice-clone
76.1 ±5.3 /100
43 participants

HeyGen study; mean and 95% participant-bootstrap interval.

Digital-twin rating · full-clone
72.6 ±5.8 /100
43 participants

Same provider study; a different mode of the same model.

Three-way preference · full-clone
41.7%
2,564 of 6,153 votes

HeyGen platform study dated October 2, 2026; Cartesia received 35.3% and ElevenLabs v4 23.0%.

Interpretation limit

HeyGen ran the digital-twin and platform studies. The 43-person ratings and 6,153-vote preference shares describe different studies and model modes. These observations do not enter weighted text-model scores. The research publication date does not establish first availability.