Development

An open voice model clones anyone in ten seconds and replies in 110ms

development2026-06-04

Claim

Miso Labs' Miso-TTS clones a voice from a ten-second clip and replies in 110 milliseconds, faster than human reaction time, while staying on-premises so enterprises keep their data in house.

Reported metric: 110 ms

Reporting date: 2026-06-04 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to June 4, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to June 4, 2026

Actor

Miso Labs

Evidence for

Supersedes

A lab ships a seventy-language live translator and a reasoning voice model

Referenced by

Cite or correct this record

Citation formatCitation text

An open voice model clones anyone in ten seconds and replies in 110ms
Innermost Loop KB — secondary record
Reporting date: 2026-06-04
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-06-04-a-voice-cloned-faster-than-reaction-time
Claim: Miso Labs' Miso-TTS clones a voice from a ten-second clip and replies in 110 milliseconds, faster than human reaction time, while staying on-premises so enterprises keep their data in house.
Attributed sources:
- Welcome to June 4, 2026 — https://theinnermostloop.substack.com/p/welcome-to-june-4-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.