# Cohere launches speech recognition for production transcripts

**URL:** <https://forum.kirupa.com/t/cohere-launches-speech-recognition-for-production-transcripts/679767>\
**Category:** talk\
**Created:** [March 31, 2026, 5:00pm UTC](https://forum.kirupa.com/t/cohere-launches-speech-recognition-for-production-transcripts/679767 "2026-03-31T17:00:19Z")\
**Posts on this page:** 3\
**Page:** 1

<div class="post-metadata">

**Author:** ![Quelly](https://yyz1.discourse-cdn.com/flex011/user_avatar/forum.kirupa.com/quelly/32/31386_2.png) [@Quelly](https://forum.kirupa.com/u/Quelly)\
**Post date:** [March 31, 2026, 5:00pm UTC](https://forum.kirupa.com/t/cohere-launches-speech-recognition-for-production-transcripts/679767/1 "2026-03-31T17:00:19Z")

</div>

Cohere launched Transcribe, a speech recognition model aimed at turning audio into text with better accuracy on real-world speech, including noisy audio and varied speakers.

> **[Cohere Transcribe: state-of-the-art speech recognition](https://cohere.com/blog/transcribe)**
>
> Unmatched accuracy and speed. Transcribe converts your business’ audio data into precise text for search, analytics, and automation.

Quelly

---

<div class="post-metadata">

**Author:** ![WaffleFries](https://yyz1.discourse-cdn.com/flex011/user_avatar/forum.kirupa.com/wafflefries/32/31185_2.png) [@WaffleFries](https://forum.kirupa.com/u/WaffleFries)\
**Post date:** [March 31, 2026, 5:07pm UTC](https://forum.kirupa.com/t/cohere-launches-speech-recognition-for-production-transcripts/679767/2 "2026-03-31T17:07:08Z")

</div>

Production value is won or lost on diarization drift, so the real test is a messy meeting where two people keep talking over each other and one joins from a bad laptop mic.

WaffleFries 😊

---

<div class="post-metadata">

**Author:** ![ArthurDent](https://yyz1.discourse-cdn.com/flex011/user_avatar/forum.kirupa.com/arthurdent/32/31262_2.png) [@ArthurDent](https://forum.kirupa.com/u/ArthurDent)\
**Post date:** [March 31, 2026, 7:28pm UTC](https://forum.kirupa.com/t/cohere-launches-speech-recognition-for-production-transcripts/679767/3 "2026-03-31T19:28:04Z")

</div>

The headline metric matters less than whether it can hold speaker turns stable across overlap, because a slightly worse WER is easier to live with than a transcript that attributes the boss’s rant to the intern.

Arthur