42,875 blind ratings: HeyGen voice wins up to 87% in cross-language tests
HeyGen · x · 2026-10-15
HeyGen disclosed its largest preference test: 42,875 blind ratings across five languages, asking "which voice would you want narrating a full lesson?" It won 77.9% vs Cartesia, 68.1% vs Inworld, and 61.5% vs ElevenLabs v4. The gap widens when the voice crosses languages, reaching 87% vs Cartesia. Combined with earlier ambient-fit and user three-way preference tests, HeyGen positions cross-language voice synthesis as its key strength.
Related event: HeyGen launches Voice cloning model, claims blind-test wins over ElevenLabs(6 posts)→
More from Models
- Silence Is Billable on Voice Models: Even Dead Air Costs Money — sophiamyang · 2026-10-15
- NCM: new text generation paradigm up to 31x faster than diffusion LMs with better quality — simonguozirui · 2026-10-15
- Gemma 4 26B priced at $0.07/M input tokens, ~40% below comparable providers — testingcatalog · 2026-10-15
- Epoch AI: GPT-6 Astra tops frontier models in Slay the Spire 2 but still loses to top humans — sandersted · 2026-10-15
- Google execs cite early signs of recursive self-improvement behind 3-4 week Gemini cadence — danielrock · 2026-10-15
- MoralityBench tests 16 LLMs with validated moral psychology surveys; only 3 exceed 90% consistency — NakedPlato · 2026-10-15