---
format: "aidr-story-markdown/v1"
id: "08eb13f492926899787cb274de18ae1654a92f9235bae112670c1dd0090c1aba"
canonical_url: "https://aidr.today/08eb13f4?lang=en"
title: "Canto: A speech model built for the real world"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-17T18:32:50.000Z"
category: "Models"
topics: ["anthropic","claude","multi-agent","open-source"]
source_urls: ["https://wisprflow.ai/canto"]
summary: "The Wispr Advanced Interfaces Lab has introduced Canto, a speech model designed for real-time dictation that achieved the lowest word error rate among tested models on real-world dictations."
---

# Canto: A speech model built for the real world

> [Open the canonical story](<https://aidr.today/08eb13f4?lang=en>)

**Published:** 2026-09-17T18:32:50.000Z
**Category:** Models
**Topics:** anthropic, claude, multi\-agent, open\-source

## Summary

The Wispr Advanced Interfaces Lab has introduced Canto, a speech model designed for real\-time dictation that achieved the lowest word error rate among tested models on real\-world dictations\.

## Sources

- [Story source](<https://wisprflow.ai/canto>)

